© 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. 72960
    Prev
    Next
    INDEX
    Explanations

    money and legal terms

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

    division, RC-Line, evolution, milestones

    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
    …
    0.57
     sweaty
    0.47
    layout
    0.47
     kinda
    0.46
     доста
    0.45
     com
    0.45
     oddly
    0.45
    c
    0.45
     hubby
    0.45
    hhh
    0.44
    POSITIVE LOGITS
    Roberts
    0.55
     사업
    0.49
    ేక
    0.49
    蒞
    0.49
    Holiday
    0.47
     വൈദ്യുതി
    0.46
    建设项目
    0.46
    AutoStabilise
    0.46
     เคย
    0.46
     ተ
    0.46
    Activations Density 0.005%

    No Known Activations