© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21355
    Prev
    Next
    INDEX
    Explanations

    Potentials, constructors, or seniors

    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
     MILITARY
    -1.29
     большинстве
    -1.19
    ambassade
    -1.16
     HAPPENED
    -1.15
    ység
    -1.13
     ECONOMIC
    -1.13
    idk
    -1.11
     subsequent
    -1.11
     geralmente
    -1.09
    
    -1.09
    POSITIVE LOGITS
     from
    1.75
     it
    1.52
     with
    1.49
     ее
    1.37
     because
    1.32
     could
    1.26
     on
    1.16
     in
    1.13
     заду
    1.11
     Its
    1.10
    Activations Density 0.462%

    No Known Activations