© 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. 95528
    Prev
    Next
    INDEX
    Explanations

    code identifiers followed by syntax

    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
     each
    -0.99
    </em>
    -0.93
     segü
    -0.93
    ,
    -0.92
     matematik
    -0.91
    quête
    -0.91
     Âge
    -0.89
    setChecked
    -0.88
     we
    -0.88
     setiap
    -0.87
    POSITIVE LOGITS
    凩
    1.03
     cúp
    1.01
    部分が
    0.99
     而
    0.93
    chose
    0.92
    discovered
    0.90
    begins
    0.90
     erfol
    0.88
     настоящий
    0.88
     forbid
    0.87
    Activations Density 0.004%

    No Known Activations