© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12572
    Prev
    Next
    INDEX
    Explanations

    hash in code contexts

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

    The neuron consistently flags occurrences of the literal string “hash” (e.g. in code identifiers or comments).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    曷
    -2.73
    ⩴
    -2.69
    腚
    -2.69
    
    -2.63
    罽
    -2.56
     nových
    -2.56
    鹋
    -2.50
    Ꭸ
    -2.36
    癟
    -2.34
    ญี่ป
    -2.33
    POSITIVE LOGITS
    to
    3.09
    ta
    2.19
    </b>
    2.13
    let
    2.08
    \
    2.03
     démocr
    2.02
     THE
    1.96
    {
    1.96
    {'
    1.96
     処
    1.95
    Activations Density 0.007%

    No Known Activations