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. 8078
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    引退
    -0.79
     shrines
    -0.74
    ts
    -0.72
     unittest
    -0.71
     Hughes
    -0.71
     GOOD
    -0.71
    inhas
    -0.71
    setLayoutParams
    -0.71
    θν
    -0.70
     hypertension
    -0.70
    POSITIVE LOGITS
     ۳۰
    1.19
     ۲۰
    1.18
     २०
    1.15
    žio
    1.12
     ২০
    1.09
    EObject
    1.06
    ۳۰
    1.05
    ₀
    1.01
    hlo
    0.99
     Lucio
    0.99
    Activations Density 0.037%

    No Known Activations