© 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. 113339
    Prev
    Next
    INDEX
    Explanations

    common phrase continuations

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

    allowed and accessible

    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
    蝣
    0.56
    藺
    0.55
    ურთ
    0.55
    🌂
    0.54
    HttpDelete
    0.52
    ❽
    0.52
    کرین
    0.52
    ྪ
    0.51
     trunc
    0.51
    خيص
    0.50
    POSITIVE LOGITS
    es
    0.56
    i
    0.50
    ist
    0.49
    ia
    0.49
     U
    0.48
    0.47
    era
    0.47
    ot
    0.46
    agel
    0.46
    est
    0.46
    Activations Density 0.001%

    No Known Activations