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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7948
    Prev
    Next
    INDEX
    Explanations

    units of length mass time energy

    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
    ऍ
    -0.81
     Valdés
    -0.75
    bunifu
    -0.73
     KOS
    -0.71
     FormGroup
    -0.70
    อ้างอิง
    -0.70
    郡
    -0.69
     Viola
    -0.69
    مشاه
    -0.68
    ➡
    -0.67
    POSITIVE LOGITS
     length
    1.59
     volume
    1.37
     distance
    1.37
     mass
    1.34
     lengths
    1.32
     Length
    1.31
     energy
    1.27
    Length
    1.23
     time
    1.20
    length
    1.18
    Activations Density 0.037%

    No Known Activations