© 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. 200731
    Prev
    Next
    INDEX
    Explanations

    uk pounds

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

    disclaimers or limitations

    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
     न्या
    0.48
    ných
    0.48
     îns
    0.45
    晹
    0.45
    嚿
    0.44
    醅
    0.44
     JI
    0.43
     Harmon
    0.43
     EDTA
    0.43
     harmon
    0.42
    POSITIVE LOGITS
    queue
    0.48
    кли
    0.48
    getBlock
    0.48
    рга
    0.47
    Ꮀ
    0.47
     mesma
    0.46
    LinkClicked
    0.46
    screenshot
    0.46
    unpublished
    0.45
    кто
    0.45
    Activations Density 0.000%

    No Known Activations