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. 42
    Prev
    Next
    INDEX
    Explanations

    non-latin characters and code

    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
    (&(
    -0.84
     architects
    -0.73
     ľ
    -0.72
    FIL
    -0.71
    steel
    -0.68
     queima
    -0.67
    Senha
    -0.67
    豐
    -0.66
     màng
    -0.66
    ziehungs
    -0.66
    POSITIVE LOGITS
    永
    0.65
    LORE
    0.64
     strength
    0.63
     lair
    0.63
    ldr
    0.62
    Strength
    0.61
     deposed
    0.60
     AVOID
    0.60
     取
    0.60
     повер
    0.60
    Activations Density 0.085%

    No Known Activations