© 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. 104400
    Prev
    Next
    INDEX
    Explanations

    digital object identifiers

    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
     for
    -2.95
     with
    -2.81
     in
    -2.77
     on
    -2.41
     when
    -2.38
    ;
    -2.34
     from
    -2.34
     out
    -2.08
     before
    -1.96
     at
    -1.91
    POSITIVE LOGITS
     spektak
    2.05
     seraient
    1.92
    킁
    1.91
     dizaines
    1.91
    ⡑
    1.90
     magnifiques
    1.89
    냑
    1.88
    ⡸
    1.86
    ドキドキ
    1.85
     centaines
    1.84
    Activations Density 0.001%

    No Known Activations