© 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. 148370
    Prev
    Next
    INDEX
    Explanations

    units of measure and practical considerations

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

    die twice, dwarven, failures to, almost always

    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
    ﻓ
    0.59
    ﻜ
    0.56
    ﺪ
    0.53
     Molina
    0.53
    ビデオ
    0.52
    ﺘ
    0.52
    ва
    0.50
     recob
    0.50
    ﹊
    0.49
    מו
    0.48
    POSITIVE LOGITS
    ụy
    0.54
    Exec
    0.47
    ssa
    0.46
     offent
    0.46
    Disp
    0.45
     fejl
    0.45
    WebApp
    0.45
    Add
    0.44
     дис
    0.44
     แล
    0.44
    Activations Density 0.001%

    No Known Activations