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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7751
    Prev
    Next
    INDEX
    Explanations

    technical descriptions with `which`

    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
     splinter
    -0.79
    Zacks
    -0.69
     leal
    -0.66
     bougie
    -0.65
    Iva
    -0.65
     mutable
    -0.65
     Learners
    -0.65
    Lời
    -0.65
    Мор
    -0.64
     oration
    -0.64
    POSITIVE LOGITS
    Submitted
    0.73
     Turtle
    0.68
    User
    0.66
    qus
    0.65
     Ingredients
    0.65
     light
    0.65
    xiety
    0.63
     szok
    0.63
    Suck
    0.63
     dương
    0.63
    Activations Density 0.085%

    No Known Activations