© 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. 29671
    Prev
    Next
    INDEX
    Explanations

    excess or degree

    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
    т
    0.67
     मा
    0.59
     Mc
    0.59
     Konfl
    0.59
     Asthma
    0.57
     т
    0.56
    秅
    0.56
     त्व
    0.55
     Ashken
    0.55
     मृ
    0.55
    POSITIVE LOGITS
    -
    0.54
    .
    0.50
    david
    0.48
    a
    0.48
    in
    0.48
    ar
    0.47
    Cancel
    0.46
    financ
    0.46
    weis
    0.45
     filament
    0.45
    Activations Density 0.088%

    No Known Activations