© 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. 14302
    Prev
    Next
    INDEX
    Explanations

    code and mixed languages

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

    The neuron fires on words and phrases meaning “help” or “suggest,” i.e. expressions offering assistance or advice.

    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
    s
    -2.61
    e
    -2.58
    ᠊
    -2.56
    ↵
    -2.53
    derdag
    -2.48
    齪
    -2.45
    蛧
    -2.42
    𓋼
    -2.33
    萏
    -2.31
    鼷
    -2.19
    POSITIVE LOGITS
    綃
    2.48
     However
    2.48
    (
    2.41
    O
    2.39
    *
    2.38
     Which
    2.31
    蟶
    2.28
    </td>
    2.22
    *.
    2.20
     If
    2.19
    Activations Density 0.000%

    No Known Activations