© 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. 113188
    Prev
    Next
    INDEX
    Explanations

    in the subject line

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

    defining terms after colon

    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
     суу
    0.49
     PARTIC
    0.48
    笃
    0.47
     акку
    0.47
    𝐷
    0.46
    
    0.46
    IT
    0.45
     PROTE
    0.45
     ég
    0.44
    D
    0.44
    POSITIVE LOGITS
     بلکہ
    0.47
     uttered
    0.46
     bets
    0.45
     handcuffed
    0.44
     rescind
    0.44
     emitida
    0.44
     withdrawals
    0.43
    bets
    0.43
     repatriation
    0.43
     cupboard
    0.42
    Activations Density 0.000%

    No Known Activations