© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123050
    Prev
    Next
    INDEX
    Explanations

    appeal for information

    np_acts-logits-general · gemini-2.5-flash-lite

    rewritten or corrected versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    0.53
    TOP
    0.48
    Quel
    0.47
    Tera
    0.46
    Vista
    0.45
    Pro
    0.44
     braucht
    0.44
    ・
    0.44
    Fax
    0.43
    )
    0.43
    POSITIVE LOGITS
    ടൊപ്പം
    0.44
    νονται
    0.40
     bolognese
    0.40
     Eminem
    0.38
     bulunduğu
    0.38
    ლები
    0.38
    ंटिक
    0.38
     bilin
    0.38
     entrambe
    0.38
    өт
    0.38
    Activations Density 0.000%

    No Known Activations