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. 8255
    Prev
    Next
    INDEX
    Explanations

    usage of 'herein'

    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
    అ
    -0.77
    Inline
    -0.75
    中途
    -0.71
    🛫
    -0.71
    SPATH
    -0.71
     واح
    -0.71
    続けて
    -0.70
     sapore
    -0.69
    EZ
    -0.68
     Inline
    -0.67
    POSITIVE LOGITS
    yty
    0.73
    留言
    0.62
    ouwen
    0.62
     переписи
    0.61
     Freizeit
    0.60
     Travers
    0.60
    Roast
    0.60
     sociologists
    0.60
     bargain
    0.60
     shielding
    0.60
    Activations Density 0.055%

    No Known Activations