© 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. 34-GEMMASCOPE-RES-131K
    7. 107323
    Prev
    Next
    INDEX
    Explanations

    method call or type definition

    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
     CERTAIN
    -1.17
    ifice
    -1.02
     Chambres
    -1.00
    𐄁
    -0.99
    Deserialize
    -0.98
     Mejor
    -0.96
    RRRR
    -0.95
    iiiii
    -0.94
    ifers
    -0.94
    incident
    -0.94
    POSITIVE LOGITS
     new
    1.29
     should
    1.26
     ((
    1.11
    ),
    1.02
     //$
    1.02
     or
    1.00
     but
    1.00
     so
    0.99
     perspectivas
    0.97
     as
    0.95
    Activations Density 0.008%

    No Known Activations