© 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. 84327
    Prev
    Next
    INDEX
    Explanations

    warranty, charity, days, boss

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

    lists, formatting, lines, words

    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
     hạt
    0.48
    يرو
    0.47
     చేశారు
    0.46
    ರೇ
    0.46
    మ్యాచ్
    0.46
    鑷
    0.46
    సిన
    0.46
    SIZ
    0.46
    豺
    0.45
    })-\
    0.45
    POSITIVE LOGITS
     thousands
    0.52
     distinction
    0.52
    ->
    0.47
    -
    0.45
    thousands
    0.44
    --
    0.44
     قض
    0.44
    ))
    0.43
    贪
    0.43
     سود
    0.43
    Activations Density 0.001%

    No Known Activations