© 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. 132315
    Prev
    Next
    INDEX
    Explanations

    newbie anymore

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

    infection, Final, bytes, thoughtful

    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
    計劃
    0.54
     )
    0.53
    ONG
    0.51
     walk
    0.50
    计划
    0.49
    ണ്ഡി
    0.48
    )
    0.48
    distribution
    0.48
     distribution
    0.47
    橫
    0.46
    POSITIVE LOGITS
    сиона
    0.53
     самостоя
    0.52
     бө
    0.52
    FBSDKInternal
    0.52
    னின்
    0.51
     инфек
    0.51
     unmet
    0.51
     infecting
    0.51
    <unused32>
    0.50
     BVHTree
    0.50
    Activations Density 0.001%

    No Known Activations