© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 158820
    Prev
    Next
    INDEX
    Explanations

    crime against

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

    word endings

    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
    ü
    0.55
    ğmen
    0.51
     التحكم
    0.50
     تنظيم
    0.48
     foglie
    0.48
    मीडिया
    0.48
     inversiones
    0.47
    𒅎
    0.47
     matematika
    0.47
     informativa
    0.47
    POSITIVE LOGITS
     bowl
    0.48
    ўні
    0.46
    box
    0.46
     box
    0.46
     име
    0.44
    ковым
    0.44
    ッセージ
    0.43
    쌌
    0.43
    เชสเตอร์
    0.42
    쳤
    0.42
    Activations Density 0.000%

    No Known Activations