© 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. 23322
    Prev
    Next
    INDEX
    Explanations

    you followed by instruction

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

    documents and conditions

    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
    ースト
    0.44
     outfitted
    0.42
    龟
    0.42
    કામાં
    0.41
    タミン
    0.41
     tessel
    0.40
     nitrile
    0.40
    榄
    0.39
    ার্জন
    0.38
     mixtape
    0.38
    POSITIVE LOGITS
    Record
    0.44
    penalty
    0.43
    record
    0.42
    AUTH
    0.42
    èvement
    0.41
    uses
    0.40
    owners
    0.40
    suggestion
    0.40
     Boot
    0.40
     Toll
    0.39
    Activations Density 0.001%

    No Known Activations