© 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. 124446
    Prev
    Next
    INDEX
    Explanations

    John Jones

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

    specific rules

    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
     calyce
    0.55
     regenv
    0.51
     tentang
    0.50
     dakkh
    0.50
     tanpa
    0.49
    🏏
    0.49
     עם
    0.49
     Kyrgios
    0.48
     pertenece
    0.48
     renderEncoder
    0.48
    POSITIVE LOGITS
    حت
    0.59
    I
    0.56
    hala
    0.51
    Cob
    0.50
    ക
    0.49
    Lessons
    0.46
    Laser
    0.45
    Drawing
    0.45
    لا
    0.44
    System
    0.44
    Activations Density 0.000%

    No Known Activations