© 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. 195452
    Prev
    Next
    INDEX
    Explanations

    product packaging and data

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

    prohibited content generation

    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
    ر
    0.44
     заяв
    0.44
     নেওয়ার
    0.42
     নেয়ার
    0.41
     Operated
    0.40
    ження
    0.40
    r
    0.39
     Williams
    0.39
     yielded
    0.38
    ший
    0.38
    POSITIVE LOGITS
     dyspe
    0.45
     sciatica
    0.44
     ಮಕ್ಕ
    0.44
     スカート
    0.43
     end
    0.43
    奧
    0.43
    っき
    0.42
     ricotta
    0.42
     ਕ
    0.41
    eosin
    0.41
    Activations Density 0.000%

    No Known Activations