© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59609
    Prev
    Next
    INDEX
    Explanations

    programming languages and code

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

    The neuron flags capitalized identifiers and proper‐name tokens (e.g. class names, acronyms, library/package names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     delikat
    -1.42
     Beweg
    -1.26
     sebagainya
    -1.23
     arī
    -1.23
    éster
    -1.20
    清晨
    -1.20
     methodical
    -1.18
     dieną
    -1.15
     duża
    -1.14
     noteworthy
    -1.13
    POSITIVE LOGITS
    no
    1.42
     aussitôt
    1.28
    *}{
    1.27
     kontakta
    1.17
     blom
    1.16
    chè
    1.16
     sata
    1.16
     orde
    1.16
    ÍC
    1.11
     seksi
    1.10
    Activations Density 0.186%

    No Known Activations