© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 106859
    Prev
    Next
    INDEX
    Explanations

    torpedo and its attacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    U
    0.59
    R
    0.52
     salmon
    0.51
    いつでも
    0.49
    AIR
    0.48
    OR
    0.47
    ू
    0.47
    F
    0.47
    SH
    0.46
    M
    0.46
    POSITIVE LOGITS
    د
    0.66
    娯
    0.49
     variado
    0.49
     něm
    0.49
     resultado
    0.48
    д
    0.47
    泂
    0.47
     finales
    0.46
    dans
    0.46
    泺
    0.46
    Activations Density 0.000%

    No Known Activations