© 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. 180231
    Prev
    Next
    INDEX
    Explanations

    short films and analysis

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

    ensures consistent delivery

    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
    Negative Logits
    tLogRow
    0.50
     או
    0.50
     סי
    0.49
     kapcsolat
    0.47
     recompens
    0.46
     לב
    0.46
     निर्यात
    0.46
    อะไร
    0.45
     ఐ
    0.44
     פ
    0.43
    POSITIVE LOGITS
     and
    0.63
    and
    0.50
    unique
    0.50
    se
    0.48
    ;
    0.48
     и
    0.47
    而
    0.46
     while
    0.45
    he
    0.44
    std
    0.44
    Activations Density 0.001%

    No Known Activations