© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 1083
    Prev
    Next
    INDEX
    Explanations

    date and time formats

    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_53_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
     gacchati
    0.48
    澀
    0.46
     стаў
    0.42
     化粧
    0.42
    псо
    0.41
     vuccanti
    0.41
    <unused79>
    0.40
    ाब
    0.40
    鸩
    0.40
     QVector
    0.40
    POSITIVE LOGITS
     MM
    0.98
    MM
    0.96
    dd
    0.95
     dd
    0.90
     DD
    0.87
    DD
    0.86
     HH
    0.85
     mm
    0.84
    mm
    0.82
     hh
    0.77
    Activations Density 0.024%

    No Known Activations