© 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. 38933
    Prev
    Next
    INDEX
    Explanations

    introducing lists or items

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

    programming and concepts

    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
    variety
    0.45
    كي
    0.45
    व्यवस्था
    0.45
    넉
    0.43
    geoning
    0.40
    })
    0.40
    땔
    0.40
    原材料
    0.39
    嶌
    0.39
    יום
    0.39
    POSITIVE LOGITS
     ประกอบ
    0.57
     สอน
    0.52
    AY
    0.51
     Bình
    0.50
     Sánchez
    0.49
     Weierstrass
    0.49
    Fig
    0.49
     നന്ന
    0.49
     действий
    0.48
     Lehrer
    0.48
    Activations Density 0.000%

    No Known Activations