© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6193
    Prev
    Next
    INDEX
    Explanations

    don't, didn't

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

    all some different

    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_53_width_65k_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
     ebenfalls
    0.34
     ส
    0.31
    Ĭ
    0.29
     european
    0.28
    <unused62>
    0.28
    Req
    0.28
    向け
    0.28
     compter
    0.28
    Հ
    0.28
     デ
    0.27
    POSITIVE LOGITS
     journalists
    0.32
     bureaucrats
    0.28
     pundits
    0.27
     complacency
    0.26
     reporters
    0.26
    acency
    0.26
     doubting
    0.26
     informing
    0.26
     complementarity
    0.26
    astically
    0.26
    Activations Density 0.035%

    No Known Activations