© 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. 60147
    Prev
    Next
    INDEX
    Explanations

    He verb

    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
     et
    -1.83
     of
    -1.74
     on
    -1.59
    jusqu
    -1.59
     between
    -1.56
    ang
    -1.51
    From
    -1.38
    Between
    -1.31
     Gemeinder
    -1.30
     @
    -1.30
    POSITIVE LOGITS
     الاطلاع
    1.51
     Cambio
    1.49
    柊
    1.46
    子は
    1.46
     Resmi
    1.44
    ⸰
    1.43
     Manten
    1.42
     Lider
    1.42
    莇
    1.41
    tiest
    1.38
    Activations Density 0.035%

    No Known Activations