© 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. 34-GEMMASCOPE-RES-131K
    7. 30834
    Prev
    Next
    INDEX
    Explanations

    Month: or 2x scales

    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
     at
    -1.91
     with
    -1.91
     in
    -1.80
     by
    -1.72
     from
    -1.62
     and
    -1.58
     on
    -1.58
     during
    -1.55
     over
    -1.52
     as
    -1.48
    POSITIVE LOGITS
    ఽ
    1.64
     mété
    1.62
    ਗ਼
    1.57
    튿
    1.53
    厹
    1.45
     délais
    1.45
    傒
    1.43
    
    1.42
     ポーチ
    1.41
     véritables
    1.41
    Activations Density 0.000%

    No Known Activations