© 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. 89505
    Prev
    Next
    INDEX
    Explanations

    Boulder, Santa Monica

    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
    ри
    0.86
    зы
    0.80
    ні
    0.78
    드를
    0.77
    ول
    0.76
    си
    0.76
    도
    0.73
     و
    0.71
     иг
    0.70
    isPartOf
    0.69
    POSITIVE LOGITS
    m
    1.05
    t
    0.98
    س
    0.96
    ↵↵
    0.95
    s
    0.92
    K
    0.91
    -
    0.88
    z
    0.87
    et
    0.86
                   
    0.84
    Activations Density 0.000%

    No Known Activations