© 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. 121001
    Prev
    Next
    INDEX
    Explanations

    contact us by phone

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

    integrated quotes, options, levels

    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
    我去
    0.46
     Compression
    0.45
    Compression
    0.45
    ညီ
    0.44
    考
    0.43
    ळी
    0.43
    欒
    0.43
    潾
    0.43
    лиги
    0.43
    信号
    0.43
    POSITIVE LOGITS
    ו
    0.49
    ق
    0.48
     inclu
    0.47
     vrouw
    0.46
     opening
    0.46
    ković
    0.46
    اه
    0.46
    ק
    0.46
    𝐚
    0.45
    و
    0.44
    Activations Density 0.000%

    No Known Activations