© 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. 181251
    Prev
    Next
    INDEX
    Explanations

    sequence prediction

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

    semicolons, used, begotten, Moore, service history

    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
    remarks
    0.52
     ++;
    0.48
     xâm
    0.46
    closed
    0.45
     tuổi
    0.45
    geom
    0.45
    ಿಸಬಹುದು
    0.44
     形
    0.44
     ತೋ
    0.44
     الإنسان
    0.44
    POSITIVE LOGITS
    ક
    0.54
    ุ
    0.49
    าส
    0.47
    яна
    0.47
    اتها
    0.46
     araştırm
    0.46
    ą
    0.45
    정과
    0.45
    ટ
    0.45
    at
    0.45
    Activations Density 0.000%

    No Known Activations