© 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. 22-GEMMASCOPE-RES-131K
    7. 15491
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    unistd
    -0.93
     anspruchs
    -0.87
    angkutan
    -0.84
     to
    -0.84
     Krankheiten
    -0.83
    liku
    -0.81
     those
    -0.81
     />';
    -0.80
     aki
    -0.80
    calib
    -0.80
    POSITIVE LOGITS
    érieurs
    0.86
    bage
    0.85
     recomendable
    0.84
     القلب
    0.82
    vdots
    0.82
     améli
    0.82
     tantos
    0.82
    avyzd
    0.82
     nation
    0.81
    時点で
    0.81
    Activations Density 0.057%

    No Known Activations