© 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. 105565
    Prev
    Next
    INDEX
    Explanations

    local members

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

    kangen water, mercenary, ethical, URL, company

    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
     lèvres
    0.57
     หนังสือ
    0.51
    countries
    0.50
    ๒
    0.49
    лся
    0.49
    埬
    0.49
     persec
    0.48
    منا
    0.48
    -,
    0.47
    underline
    0.46
    POSITIVE LOGITS
     disappeared
    0.50
    ਾ
    0.50
     SEL
    0.46
     delivered
    0.46
     propagates
    0.45
    元年
    0.45
    SEL
    0.44
    rescent
    0.44
     vanished
    0.44
     interconnection
    0.43
    Activations Density 0.000%

    No Known Activations