© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112105
    Prev
    Next
    INDEX
    Explanations

    next level or step

    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_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
     parachoque
    -1.82
    𖤣
    -1.80
     veranderen
    -1.69
    鼷
    -1.63
    狲
    -1.61
     entregado
    -1.61
     शुर
    -1.56
     lebte
    -1.55
     أيض
    -1.55
     and
    -1.55
    POSITIVE LOGITS
     of
    2.36
     they
    1.83
    ли
    1.80
    原因
    1.72
     другие
    1.67
    www
    1.65
    “
    1.59
    >
    1.55
     dirigeants
    1.54
     уже
    1.52
    Activations Density 0.019%

    No Known Activations