© 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. 83467
    Prev
    Next
    INDEX
    Explanations

    early withdrawals, insurance, poetry, Korean, French

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

    academic and technical concepts

    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
     संकट
    0.55
    ,‎
    0.46
    रल
    0.44
     extradition
    0.44
    OV
    0.43
     Welfare
    0.43
    Cmd
    0.43
     ParkingLot
    0.43
    '=>'','
    0.43
    UI
    0.42
    POSITIVE LOGITS
     titres
    0.46
     사람들이
    0.46
     mensen
    0.45
     avaient
    0.45
     strictement
    0.45
     voltam
    0.44
    경상
    0.44
     énorme
    0.44
    敷
    0.44
    atica
    0.43
    Activations Density 0.001%

    No Known Activations