© 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. 133077
    Prev
    Next
    INDEX
    Explanations

    specific word pairings

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

    sellers using API

    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
    geq
    0.60
     arrond
    0.53
     الصنا
    0.50
    ம்பெ
    0.49
    ()).
    0.48
    ।
    0.48
     Braunschweig
    0.48
     Sén
    0.47
     \%)$.
    0.46
    ることが
    0.46
    POSITIVE LOGITS
    ere
    0.52
    ien
    0.51
    ene
    0.51
    assie
    0.49
    ek
    0.49
     wood
    0.49
    ela
    0.48
    ท
    0.48
    ande
    0.48
     നിര
    0.48
    Activations Density 0.000%

    No Known Activations