© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 142945
    Prev
    Next
    INDEX
    Explanations

    foreign keys and primary keys

    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
    發現
    0.74
    贛
    0.72
    лка
    0.69
    ロボ
    0.68
     కొత్త
    0.67
    ಲ್ಲು
    0.65
    企業
    0.64
    數
    0.63
    中
    0.62
    𒅌
    0.61
    POSITIVE LOGITS
    il
    0.60
    ap
    0.58
     to
    0.57
    apolitan
    0.56
    id
    0.55
    apin
    0.54
     punctual
    0.52
    ing
    0.52
    queous
    0.52
    ir
    0.52
    Activations Density 0.002%

    No Known Activations