© 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. 159004
    Prev
    Next
    INDEX
    Explanations

    firm commitment

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

    technical formatting and code

    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
    ･
    0.42
    萩
    0.42
    лма
    0.42
    ни
    0.41
    匏
    0.41
    刂
    0.41
    שׁ
    0.40
    лля
    0.40
    钨
    0.40
    ӗ
    0.39
    POSITIVE LOGITS
     são
    0.45
     a
    0.45
     evidente
    0.45
     temos
    0.45
     estão
    0.44
     estamos
    0.44
     😉
    0.43
     an
    0.43
     empr
    0.43
     maîtr
    0.42
    Activations Density 0.000%

    No Known Activations