© 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. 208576
    Prev
    Next
    INDEX
    Explanations

    rule, glue, history, screaming, soda, lost, houses

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

    Generation:**, AUR (, Packages, Instance 1, Functions:

    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
    t
    0.60
    is
    0.47
    完美的
    0.47
    or
    0.44
    Cours
    0.44
    riched
    0.44
    hept
    0.44
    icleta
    0.44
    稟
    0.43
    serious
    0.43
    POSITIVE LOGITS
     いたし
    0.53
     arrêter
    0.49
     kriminal
    0.49
     Joaquín
    0.48
    篾
    0.47
     discriminant
    0.46
     órdenes
    0.46
     ঝড়
    0.45
     Franti
    0.45
    ผู้ชมในสนาม
    0.44
    Activations Density 0.000%

    No Known Activations