Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 9
    Prev
    Next
    INDEX
    Explanations

    URLs and academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    得分
    -0.76
     medži
    -0.73
     нашли
    -0.69
    ஓ
    -0.68
    botten
    -0.68
     متری
    -0.67
    槽
    -0.67
    Ya
    -0.66
     Quiz
    -0.66
    וע
    -0.65
    POSITIVE LOGITS
    ifiable
    0.76
     sembler
    0.69
    sqcup
    0.69
     Verv
    0.67
    ствует
    0.65
     István
    0.65
    ije
    0.64
    خت
    0.64
    هاز
    0.63
     Tomo
    0.63
    Activations Density 0.093%

    No Known Activations