© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 26884
    Prev
    Next
    INDEX
    Explanations

    numbers followed by data

    np_acts-logits-general · gemini-2.5-flash-lite

    early limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ভাল
    0.47
    রাজ
    0.45
     nhà
    0.44
     ল
    0.43
     ру
    0.43
    店铺
    0.42
    িল
    0.42
    ली
    0.42
    ру
    0.41
     পড়িয়া
    0.41
    POSITIVE LOGITS
    ceso
    0.50
     resonant
    0.45
    iciable
    0.43
     moisture
    0.42
     needless
    0.41
     radiation
    0.40
    emptive
    0.40
     unanticipated
    0.40
    SpecID
    0.39
     bursting
    0.39
    Activations Density 0.000%

    No Known Activations