© 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. 153685
    Prev
    Next
    INDEX
    Explanations

    news, analysis, strategy

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

    super vs. normal

    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
    voll
    0.54
    ates
    0.49
    andom
    0.49
    ল
    0.48
    lens
    0.46
    आज
    0.46
    orbit
    0.46
    inv
    0.46
    områ
    0.46
    र्द
    0.45
    POSITIVE LOGITS
     бывает
    0.51
     段
    0.49
     किन्न
    0.47
     جائزہ
    0.47
     ورزش
    0.46
     וא
    0.45
     حرکت
    0.43
     cercare
    0.43
     começ
    0.43
    ચાર
    0.43
    Activations Density 0.001%

    No Known Activations