© 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. 197134
    Prev
    Next
    INDEX
    Explanations

    production and subsequent action

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

    rebuilt tractor, healthy dynamic, beautiful wildflower

    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
    mu
    0.58
    board
    0.53
     에
    0.52
    boards
    0.52
     п
    0.51
    module
    0.50
     ג
    0.49
     도
    0.49
    crypto
    0.49
    mid
    0.49
    POSITIVE LOGITS
    نة
    0.55
    േഷ്
    0.55
    ივ
    0.54
     scepticism
    0.54
    رفة
    0.52
    ResponseType
    0.52
    اة
    0.51
    та
    0.50
     restlessness
    0.50
    覚
    0.50
    Activations Density 0.000%

    No Known Activations