© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 148724
    Prev
    Next
    INDEX
    Explanations

    financial year, halftime, singles

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

    muscle activation

    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
     acompañado
    0.47
     gleichzeitig
    0.47
    திகளை
    0.46
    εν
    0.46
     recibieron
    0.45
     esperaba
    0.45
     recogida
    0.45
    ⎥
    0.44
    >.
    0.44
     obligatoire
    0.44
    POSITIVE LOGITS
     crack
    0.45
    dresser
    0.44
    Marion
    0.44
     фра
    0.44
    uação
    0.43
    來越
    0.43
    serif
    0.41
    hton
    0.41
     hairline
    0.41
     ราศี
    0.40
    Activations Density 0.001%

    No Known Activations