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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40076
    Prev
    Next
    INDEX
    Explanations

    language diversity

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

    The neuron highlights highly technical scientific terms and methods (e.g. gene, sequencing, phylogenetic analysis, spectroscopies).

    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
     who
    -1.86
     which
    -1.66
     whom
    -1.45
     oberen
    -1.37
     only
    -1.36
    вање
    -1.33
     Without
    -1.32
    踴
    -1.31
    蘊
    -1.30
     چون
    -1.30
    POSITIVE LOGITS
     PUEDE
    1.52
     mogelijkheid
    1.48
     a
    1.41
     belangrijke
    1.37
    during
    1.30
     sukses
    1.30
     parlent
    1.27
     jellemző
    1.26
    geht
    1.24
    zelfde
    1.23
    Activations Density 0.190%

    No Known Activations