© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2701
    Prev
    Next
    INDEX
    Explanations

    settings paths

    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_40_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
     Einwill
    0.50
    祹
    0.50
     Activision
    0.49
    勰
    0.49
    akaran
    0.49
    <unused1808>
    0.48
    ЕМ
    0.48
     Marissa
    0.48
     nigris
    0.47
     протя
    0.47
    POSITIVE LOGITS
    fn
    0.55
    vertical
    0.50
    \
    0.48
    fuel
    0.47
    ↵
    0.47
    lat
    0.47
    scale
    0.47
    high
    0.46
    '
    0.46
    0.46
    Activations Density 0.000%

    No Known Activations