© 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. 85346
    Prev
    Next
    INDEX
    Explanations

    use/allow/enable followed by a noun

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

    The neuron fires on uppercase code/configuration option names (often with trailing underscores) and boolean‐style flag tokens.

    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
    .'-
    -1.53
    "")
    -1.45
    "";
    -1.44
    🏀
    -1.38
    ⃣
    -1.38
    "+
    -1.38
    ='';
    -1.36
    '';
    -1.34
    ***/
    -1.33
    `;
    -1.32
    POSITIVE LOGITS
    6
    1.68
    Also
    1.59
    0
    1.55
     only
    1.52
    However
    1.51
    7
    1.49
    8
    1.41
     for
    1.34
    When
    1.32
    ત્ર
    1.30
    Activations Density 0.056%

    No Known Activations