© 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. 156824
    Prev
    Next
    INDEX
    Explanations

    big high

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

    defining qualities and purposes

    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
    "
    0.48
    o
    0.44
    vening
    0.44
    oning
    0.44
    cribes
    0.44
    FIA
    0.43
    བ་
    0.42
    asd
    0.41
    ot
    0.41
    (
    0.41
    POSITIVE LOGITS
     изме
    0.52
     завое
    0.52
     нео
    0.51
     нашим
    0.49
     модерни
    0.46
     чувстви
    0.46
    диви
    0.46
     Наши
    0.46
     перво
    0.46
     bessere
    0.46
    Activations Density 0.000%

    No Known Activations