© 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. 199482
    Prev
    Next
    INDEX
    Explanations

    trademarks and product names

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

    academic and professional contexts

    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
     एकूण
    0.50
    げ
    0.48
    हिंदी
    0.48
     getName
    0.47
     ممالک
    0.47
    گیا
    0.47
    inputs
    0.46
    wins
    0.45
    anguages
    0.45
    वुड
    0.45
    POSITIVE LOGITS
     Maxi
    0.45
    擂
    0.44
     Joey
    0.44
    控
    0.43
    跡
    0.42
    ically
    0.42
     Ely
    0.42
     Bastian
    0.42
     atrás
    0.41
     sonore
    0.41
    Activations Density 0.001%

    No Known Activations