© 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-65K
    7. 2749
    Prev
    Next
    INDEX
    Explanations

    dedicated X

    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_65k_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
    .
    1.38
     .
    1.11
     can
    0.97
    h
    0.96
    ?
    0.95
    א
    0.93
    ला
    0.88
    大
    0.86
    માં
    0.86
    ться
    0.86
    POSITIVE LOGITS
    н
    1.08
    ’
    1.00
    که
    0.98
    ዐይን
    0.94
    کرد
    0.93
    W
    0.93
    вір
    0.92
    права
    0.91
    ین
    0.91
    وک
    0.91
    Activations Density 0.156%

    No Known Activations