© 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. 49954
    Prev
    Next
    INDEX
    Explanations

    available partners actors label

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

    nature of attack, cause of looseness, binary search

    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
     usw
    0.49
    ન્મ
    0.45
     vork
    0.45
    =
    0.44
    Если
    0.44
     allowances
    0.44
    !
    0.44
    🧍
    0.43
    Jeśli
    0.42
     malu
    0.42
    POSITIVE LOGITS
     fecund
    0.47
     ಕೆಲವು
    0.46
     చివరి
    0.45
     مزاج
    0.44
    さい
    0.43
    訴
    0.43
    霞
    0.43
     ಖರೀ
    0.42
     hysteria
    0.42
     जुन
    0.42
    Activations Density 0.001%

    No Known Activations