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. 8029
    Prev
    Next
    INDEX
    Explanations

    percentages and changes

    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
     which
    -1.09
    canActivate
    -0.95
    ModelAndView
    -0.91
    haltet
    -0.89
    MultipartFile
    -0.86
     Decken
    -0.86
    onload
    -0.85
     tiroirs
    -0.83
    Callback
    -0.83
     jendela
    -0.82
    POSITIVE LOGITS
     to
    2.27
     at
    1.63
     settle
    1.01
    figurine
    0.99
    cmos
    0.95
    stanley
    0.92
    pioneer
    0.91
    valentine
    0.90
    oriental
    0.90
    Settle
    0.89
    Activations Density 0.012%

    No Known Activations