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. 7898
    Prev
    Next
    INDEX
    Explanations

    length or duration

    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
     exatamente
    -0.88
    RICT
    -0.84
     into
    -0.84
     against
    -0.82
     võib
    -0.82
     tablespoons
    -0.79
     Kartoffeln
    -0.78
     理
    -0.78
     America
    -0.77
     mAh
    -0.77
    POSITIVE LOGITS
     Toast
    1.41
     duration
    1.29
     length
    1.18
    LENGTH
    1.13
     LENGTH
    1.03
     продолжи
    1.00
    Toast
    1.00
     Length
    0.99
     duración
    0.96
    Lenght
    0.94
    Activations Density 0.001%

    No Known Activations