© 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. 216549
    Prev
    Next
    INDEX
    Explanations

    reproducing stories for journalists

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

    how much

    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
     shayari
    0.56
     dedic
    0.56
     few
    0.54
     tog
    0.54
    c
    0.53
     dedication
    0.52
     o
    0.51
     fours
    0.50
     surprisingly
    0.50
     spice
    0.50
    POSITIVE LOGITS
     абсолю
    0.50
    இல்
    0.49
     ಉತ್ಪ
    0.48
     Vestone
    0.48
     базу
    0.47
    phenoxymethyl
    0.47
     Вул
    0.46
    _{-}
    0.46
    แสง
    0.46
    totalSupply
    0.46
    Activations Density 0.002%

    No Known Activations