© 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. 101354
    Prev
    Next
    INDEX
    Explanations

    really judgmental

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

    Ethereum, alcohol, quantities, repetitive

    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
    낵
    0.54
    丿
    0.53
    дам
    0.52
    정
    0.51
    КП
    0.50
    기
    0.50
    歷
    0.50
    牴
    0.49
    ாக
    0.48
     écart
    0.48
    POSITIVE LOGITS
    text
    0.51
    hz
    0.50
    h
    0.50
    hle
    0.47
     upon
    0.47
    uth
    0.47
    pg
    0.45
    hl
    0.45
    wm
    0.45
    ue
    0.45
    Activations Density 0.000%

    No Known Activations