© 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. 169900
    Prev
    Next
    INDEX
    Explanations

    bars indicate

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

    patterns and strategies

    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
     بينهم
    0.50
     ماشي
    0.49
     sichtbar
    0.48
    aldb
    0.47
    aminated
    0.46
     クリ
    0.46
    門
    0.45
    ريق
    0.44
    絆
    0.44
     blanco
    0.44
    POSITIVE LOGITS
    ciences
    0.45
     Cycles
    0.43
     Testimony
    0.43
     integrating
    0.42
     Withdraw
    0.42
     Drafting
    0.41
    ﺩ
    0.41
     Regulatory
    0.41
     કેટલી
    0.41
    ্দের
    0.41
    Activations Density 0.000%

    No Known Activations