© 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. 148938
    Prev
    Next
    INDEX
    Explanations

    wanted it

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

    NotFoundError, ML, Architect

    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
    谣
    0.54
     rumoured
    0.45
     damning
    0.45
     యుద్ధ
    0.45
     traitor
    0.44
    rok
    0.43
    これにより
    0.43
     hunk
    0.43
     crux
    0.42
    朝鲜
    0.42
    POSITIVE LOGITS
    瓔
    0.53
    4
    0.52
     HOLDERS
    0.50
    付属品
    0.47
    8
    0.47
    載
    0.46
     నిర్వహ
    0.45
    Wagner
    0.45
    襯
    0.45
    鉑
    0.45
    Activations Density 0.000%

    No Known Activations