© 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. 7657
    Prev
    Next
    INDEX
    Explanations

    version of

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

    versions and fine-tuned models

    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
    在新
    0.35
    在我
    0.35
    ันท
    0.35
    วัส
    0.34
    곶
    0.34
    ięcy
    0.34
     ষড়যন্ত্র
    0.34
    issons
    0.34
    塑造
    0.33
    Сер
    0.33
    POSITIVE LOGITS
    版的
    0.85
     version
    0.77
    版本的
    0.73
     기존
    0.70
    版
    0.69
     versions
    0.68
    通常の
    0.68
     versie
    0.67
    従来の
    0.63
     existing
    0.59
    Activations Density 0.199%

    No Known Activations