© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128179
    Prev
    Next
    INDEX
    Explanations

    code structure

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

    This neuron detects runs of whitespace at the start of lines (i.e. leading indentation).

    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
     Händen
    -1.78
    ?”
    -1.73
     REPRESENTATIVES
    -1.68
     hermosos
    -1.67
     véhicules
    -1.66
    AILABILITY
    -1.66
     Füßen
    -1.64
    ጧ
    -1.63
     zamanda
    -1.59
    ⍽
    -1.59
    POSITIVE LOGITS
    V
    2.33
    IN
    2.03
    ();
    1.99
    ";
    1.98
    J
    1.94
    IT
    1.91
    AS
    1.90
    it
    1.88
     said
    1.87
    );
    1.84
    Activations Density 0.026%

    No Known Activations