© 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. 110393
    Prev
    Next
    INDEX
    Explanations

    providers development couple directory crackers moments faucets

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

    explaining areas, issues, understanding, advice

    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
     +
    0.54
     प्रदेश
    0.45
     रोमा
    0.44
     अन्यथा
    0.43
    ographical
    0.43
    ppable
    0.43
     souhaite
    0.42
     Texture
    0.41
     deprecated
    0.41
     राष्ट्रीय
    0.40
    POSITIVE LOGITS
     eredmény
    0.45
    ابية
    0.44
    가를
    0.41
    plaf
    0.41
    سا
    0.41
    |=\
    0.41
    强的
    0.40
    Popup
    0.40
    jhelp
    0.40
    ^*(\
    0.40
    Activations Density 0.000%

    No Known Activations