© 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. 33250
    Prev
    Next
    INDEX
    Explanations

    United States

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

    highlighted phrases

    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
    Ｖ
    0.42
    ik
    0.41
     assorted
    0.41
     incentives
    0.40
    क
    0.40
    ধন
    0.40
    opened
    0.40
    鉞
    0.40
    aligned
    0.39
     avantages
    0.39
    POSITIVE LOGITS
     Mature
    0.55
     repet
    0.47
     Calcula
    0.47
     لأن
    0.46
     protože
    0.46
     திருதியை
    0.46
     द्वारा
    0.45
     بت
    0.45
     نقط
    0.45
     sout
    0.44
    Activations Density 0.000%

    No Known Activations