© 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. 73144
    Prev
    Next
    INDEX
    Explanations

    size declarations

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

    This neuron activates on the token “size” (e.g. function or variable names containing “size”) in code.

    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
     
    -2.61
    ?”
    -2.42
    </i>
    -2.41
    ”-
    -2.39
    -”
    -2.38
    ’
    -2.38
     WHILE
    -2.31
    ?”.
    -2.31
    '
    -2.31
     ビッグ
    -2.28
    POSITIVE LOGITS
    er
    3.19
    ه
    3.14
     れる
    2.47
    裡的
    2.45
    pielen
    2.42
     säga
    2.42
    ⼼
    2.41
    涜
    2.39
    𝟭
    2.38
    尋找
    2.36
    Activations Density 0.004%

    No Known Activations