© 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. 106864
    Prev
    Next
    INDEX
    Explanations

    voyage

    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
    ing
    1.39
    in
    1.24
    er
    1.12
    ed
    1.02
    ut
    0.93
    at
    0.92
    u
    0.91
    em
    0.89
    erà
    0.85
    es
    0.84
    POSITIVE LOGITS
    ка
    0.77
    𝙤
    0.70
    𝙜
    0.70
    𝙠
    0.69
    ки
    0.68
    ของ
    0.64
    ك
    0.64
    𝙣
    0.63
     Blak
    0.62
    菪
    0.62
    Activations Density 0.001%

    No Known Activations