© 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. 162343
    Prev
    Next
    INDEX
    Explanations

    glibc

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

    run the tool

    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
     تنها
    0.46
    મના
    0.46
    multirow
    0.46
     Finley
    0.45
     Hill
    0.44
     здійс
    0.44
    𝗠
    0.44
    ᅬ
    0.42
    يل
    0.42
    মোট
    0.42
    POSITIVE LOGITS
    </strong>
    0.50
    Kamu
    0.46
    activ
    0.43
    ifikat
    0.43
    ple
    0.43
    скую
    0.42
    WarningLevel
    0.42
     przec
    0.42
    hafte
    0.42
    Pwd
    0.42
    Activations Density 0.000%

    No Known Activations