© 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. 34-GEMMASCOPE-RES-131K
    7. 32661
    Prev
    Next
    INDEX
    Explanations

    quoted speech

    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_34/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
     in
    -1.58
     at
    -1.34
     their
    -1.26
     "...
    -1.25
     that
    -1.22
    〜。
    -1.21
     as
    -1.20
     what
    -1.14
     not
    -1.14
     with
    -1.14
    POSITIVE LOGITS
     famed
    1.36
     quintessential
    1.31
    gewiesen
    1.21
    <blockquote>
    1.21
     relentless
    1.20
     hordes
    1.17
     クルー
    1.16
     uovo
    1.14
     revamped
    1.14
    halts
    1.14
    Activations Density 0.010%

    No Known Activations