© 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. 21902
    Prev
    Next
    INDEX
    Explanations

    this followed by study type words

    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
     to
    -2.92
     at
    -2.05
     by
    -1.70
     $
    -1.66
    izace
    -1.47
     ž
    -1.46
     from
    -1.46
    ;
    -1.45
     १
    -1.41
     Also
    -1.40
    POSITIVE LOGITS
     bershka
    1.77
    팻
    1.69
     kablo
    1.69
     etek
    1.61
     bileklik
    1.60
     superbes
    1.60
     aksesuar
    1.57
     negru
    1.57
     regata
    1.56
     ristorante
    1.55
    Activations Density 0.145%

    No Known Activations