© 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. 153419
    Prev
    Next
    INDEX
    Explanations

    list startbook titleslinksISBNssports statistics

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

    requirements and potential risks

    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
    垁
    0.51
    ╞
    0.49
     looped
    0.49
     podmín
    0.48
     conformational
    0.47
    ญี่ป
    0.47
     theorems
    0.46
     japonesa
    0.46
    觕
    0.46
    hubungan
    0.46
    POSITIVE LOGITS
    1
    0.48
     -
    0.43
     do
    0.43
    Occupation
    0.41
    Television
    0.41
    Academy
    0.40
    Arkansas
    0.40
    迈
    0.40
     vein
    0.40
    ,
    0.40
    Activations Density 0.001%

    No Known Activations