© 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. 42481
    Prev
    Next
    INDEX
    Explanations

    consider it or opinion

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

    consider me

    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
    د
    0.80
     hypothes
    0.75
    어
    0.71
     installations
    0.70
    像
    0.69
    、
    0.66
     你
    0.65
    эй
    0.65
    经常
    0.64
    感觉到
    0.63
    POSITIVE LOGITS
    en
    1.29
    d
    1.16
    on
    1.16
    n
    1.13
    p
    1.06
    in
    1.05
    an
    1.02
    ar
    1.02
    m
    1.00
    t
    0.97
    Activations Density 0.044%

    No Known Activations