© 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. 55999
    Prev
    Next
    INDEX
    Explanations

    sealed victory

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

    occurred millennia ago

    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
    轵
    0.48
     شخصی
    0.45
     साक्षी
    0.44
     ！
    0.44
     వ్యక్తి
    0.43
    無料
    0.43
    npmjs
    0.43
    聿
    0.43
    沌
    0.43
    iyasi
    0.42
    POSITIVE LOGITS
     relocate
    0.54
     rescues
    0.53
     relocated
    0.52
     outspoken
    0.51
     electronics
    0.49
     oars
    0.49
     collapses
    0.48
     smells
    0.47
     outnumbered
    0.46
     ancestors
    0.46
    Activations Density 0.000%

    No Known Activations