© 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. 34-GEMMASCOPE-RES-131K
    4. 45603
    Prev
    Next
    INDEX
    Explanations

    code, comments, and foreign text

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

    The neuron fires on numeric literal tokens in code (e.g. integers assigned or passed in).

    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
     (
    -1.59
     from
    -1.32
     some
    -1.31
     while
    -1.30
     if
    -1.29
     those
    -1.29
     our
    -1.28
     as
    -1.26
     in
    -1.25
    その
    -1.24
    POSITIVE LOGITS
     toepassing
    1.20
     onderstaande
    1.18
    様な
    1.17
    Oph
    1.15
     voorwaarden
    1.13
    Acacia
    1.12
    alamualaikum
    1.11
     krach
    1.11
    鬟
    1.09
     skolen
    1.07
    Activations Density 0.015%

    No Known Activations