© 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. 58672
    Prev
    Next
    INDEX
    Explanations

    eject &

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

    steps and divisions

    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
    c
    0.49
    shank
    0.48
    ov
    0.46
    gor
    0.44
    os
    0.44
    AN
    0.44
    RO
    0.43
    colors
    0.43
     "")
    0.42
    ạc
    0.42
    POSITIVE LOGITS
     divisão
    0.48
     структуру
    0.47
     этап
    0.47
     раздел
    0.46
    Ἑ
    0.44
    ὃ
    0.44
     громадян
    0.44
     división
    0.43
     структура
    0.43
    \}$.
    0.42
    Activations Density 0.000%

    No Known Activations