© 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. 152529
    Prev
    Next
    INDEX
    Explanations

    index followed by quote

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

    index and key definitions

    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
    <td>
    0.46
    –
    0.46
    …
    0.44
    un
    0.38
     BitmapFactory
    0.38
    ()-
    0.38
     motorcycle
    0.37
    =
    0.37
    sunrise
    0.37
     candidate
    0.36
    POSITIVE LOGITS
     spezi
    0.52
     Middlesex
    0.51
     nach
    0.50
    FIED
    0.50
     конфигура
    0.49
    ITTING
    0.48
    楹
    0.47
    दीप
    0.47
     Niv
    0.46
    RADIATION
    0.46
    Activations Density 0.000%

    No Known Activations