© 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. 130450
    Prev
    Next
    INDEX
    Explanations

    record became, documentary entitled, certification logo

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

    Rotation, Leadership, Everything

    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
    ხ
    0.46
     as
    0.45
     riches
    0.43
     соревнования
    0.43
     piped
    0.42
     parabolic
    0.42
    エク
    0.42
    љи
    0.41
    ֙
    0.40
    ഖ
    0.40
    POSITIVE LOGITS
     Prac
    0.50
     belieb
    0.48
     Have
    0.48
     홀
    0.48
     Breathing
    0.47
    hein
    0.47
     deutschen
    0.47
    otum
    0.47
     होल
    0.46
    remen
    0.46
    Activations Density 0.000%

    No Known Activations