© 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. 166151
    Prev
    Next
    INDEX
    Explanations

    essential spiritual idea

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

    logical deduction

    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
    t
    0.60
    able
    0.50
    apartment
    0.45
     feste
    0.44
    引发
    0.44
    gget
    0.44
    b
    0.44
    ↵↵↵↵↵↵↵↵
    0.44
    ↵↵↵↵↵↵
    0.43
    brightness
    0.43
    POSITIVE LOGITS
     বিষয়ে
    0.50
     topRight
    0.48
    ۴
    0.48
    禰
    0.48
    ري
    0.48
    contrar
    0.48
    ुलम
    0.47
    Pointer
    0.46
    র্জ
    0.45
    וֹ
    0.45
    Activations Density 0.000%

    No Known Activations