© 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. 227061
    Prev
    Next
    INDEX
    Explanations

    foreign language or script

    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
    ;
    0.52
     annivers
    0.43
    )));
    0.41
    `
    0.40
    шев
    0.40
    offsetTop
    0.39
    manship
    0.39
     cau
    0.39
    igs
    0.38
     እንዲሁም
    0.38
    POSITIVE LOGITS
     இப்போது
    0.52
    ర
    0.49
    د
    0.47
    ת
    0.46
    더
    0.46
     piedras
    0.44
     এখন
    0.44
    ಙ
    0.44
    अब
    0.43
     ALG
    0.43
    Activations Density 0.002%

    No Known Activations