© 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. 16702
    Prev
    Next
    INDEX
    Explanations

    praise

    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
    s
    1.27
    1.25
    g
    0.99
    ।
    0.98
    size
    0.98
     Year
    0.98
    c
    0.96
    LET
    0.96
    b
    0.95
    RI
    0.93
    POSITIVE LOGITS
    ب
    1.26
    ти
    1.24
     praised
    1.22
    та
    1.12
    ский
    1.12
    مي
    1.11
    ك
    1.10
    ية
    1.09
    онов
    1.09
    قوم
    1.09
    Activations Density 0.003%

    No Known Activations