© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41768
    Prev
    Next
    INDEX
    Explanations

    push or pushing

    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
     will
    -1.94
    The
    -1.90
    .
    -1.88
     untuk
    -1.78
     when
    -1.70
    of
    -1.66
     we
    -1.66
    -1.65
    As
    -1.63
    #
    -1.62
    POSITIVE LOGITS
     empuj
    2.09
    龘
    2.02
    面色
    1.91
    揠
    1.85
    來
    1.81
     mismas
    1.80
     enmar
    1.78
    を使
    1.77
     incluidas
    1.77
    ୬
    1.73
    Activations Density 0.023%

    No Known Activations