© 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. 216333
    Prev
    Next
    INDEX
    Explanations

    content for

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

    trends and abilities

    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
     Liang
    0.46
     Lanz
    0.46
     /
    0.45
     a
    0.43
     Pek
    0.42
     koff
    0.42
    做
    0.42
     Sik
    0.42
    要做
    0.41
     junge
    0.40
    POSITIVE LOGITS
    s
    0.64
     स्पेश
    0.52
    sız
    0.50
     निकालकर
    0.50
    incorrect
    0.50
    aparikkh
    0.49
    ডস
    0.49
     ভাইরাল
    0.48
    INSTDIR
    0.48
    Gmail
    0.47
    Activations Density 0.001%

    No Known Activations