© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10257
    Prev
    Next
    INDEX
    Explanations

    transformation and injection efficiency

    np_acts-logits-general · gemini-2.5-flash-lite

    terminology related to genetic transformation and transfection processes in biological systems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron reliably fires on occurrences of “trans”-prefixed technical terms (e.g. transformation, transposase, transfection, transgene integration) in genetic‐engineering contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -1.58
    ">
    
    
    -1.48
     sometimes
    -1.40
    machung
    -1.39
     that
    -1.38
    }
    
    -1.36
     \&
    -1.34
    平时
    -1.32
    っていましたが
    -1.29
     sebuah
    -1.27
    POSITIVE LOGITS
     with
    1.68
     нього
    1.30
     into
    1.28
     without
    1.21
     by
    1.17
     With
    1.16
     одной
    1.15
    andidates
    1.14
     peine
    1.13
     інших
    1.13
    Activations Density 0.170%

    No Known Activations