© 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. 159923
    Prev
    Next
    INDEX
    Explanations

    jump in, apps for, missiles into

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

    foreign languages, medical terms

    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
     gravid
    0.50
     baud
    0.47
    ಿಸಿದ್ದ
    0.47
     materna
    0.46
     caram
    0.45
    CONDUCT
    0.45
     :).
    0.44
     hepinize
    0.44
     teore
    0.44
     গ্রাহ
    0.44
    POSITIVE LOGITS
    рано
    0.45
    uje
    0.45
    ехал
    0.45
     personn
    0.43
    صر
    0.41
    дено
    0.40
    엊
    0.39
     yg
    0.39
    стров
    0.39
    рованного
    0.39
    Activations Density 0.001%

    No Known Activations