© 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. 30194
    Prev
    Next
    INDEX
    Explanations

    Gecko driver or gecko rendering

    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
    .
    0.91
    ン
    0.91
    :
    0.84
    ن
    0.81
    ন
    0.80
     timestamps
    0.77
    าย
    0.75
     downloads
    0.74
     covenants
    0.68
     streamlines
    0.68
    POSITIVE LOGITS
    others
    0.98
    し
    0.96
    ac
    0.95
    five
    0.94
    после
    0.88
    ud
    0.86
    M
    0.86
    }";
    0.85
    ни
    0.84
    C
    0.84
    Activations Density 0.001%

    No Known Activations