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. 8053
    Prev
    Next
    INDEX
    Explanations

    angles and degrees

    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
    clientHeight
    -0.91
     rollover
    -0.87
     hilfreich
    -0.83
    ˥
    -0.80
     Floral
    -0.78
     boycot
    -0.78
     ayude
    -0.78
    addOn
    -0.77
     движения
    -0.77
     Alu
    -0.75
    POSITIVE LOGITS
     angle
    1.65
     angles
    1.34
    角度
    0.99
     sixty
    0.97
    angle
    0.94
     Angle
    0.93
    Angle
    0.91
     spread
    0.89
     Sixty
    0.86
    angles
    0.85
    Activations Density 0.027%

    No Known Activations