© 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. 66818
    Prev
    Next
    INDEX
    Explanations

    describing appearance or state

    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
    c
    -1.83
    as
    -1.62
    g
    -1.55
    ъ
    -1.54
     mondeo
    -1.52
    %
    -1.51
     fabia
    -1.49
     poursuivre
    -1.48
    Now
    -1.44
    :
    -1.43
    POSITIVE LOGITS
     in
    1.92
    mıştır
    1.41
     that
    1.41
     possibly
    1.37
     their
    1.36
     perhaps
    1.32
     Berechnung
    1.30
     autores
    1.30
     condenado
    1.30
    matism
    1.29
    Activations Density 0.022%

    No Known Activations