© 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. 22-GEMMASCOPE-RES-131K
    7. 68266
    Prev
    Next
    INDEX
    Explanations

    common word followed by specific word

    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_22/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
     one
    -1.22
    what
    -1.20
     by
    -1.18
     from
    -1.17
    أت
    -1.15
     because
    -1.12
     without
    -1.12
    oluzione
    -1.10
     any
    -1.07
    from
    -1.04
    POSITIVE LOGITS
    <bos>
    1.22
     plaisir
    1.02
    ʻ
    0.98
     hinten
    0.97
    ències
    0.96
     gött
    0.96
     در
    0.95
     maravill
    0.93
     ABSOL
    0.93
    getNombre
    0.93
    Activations Density 0.000%

    No Known Activations