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. 8373
    Prev
    Next
    INDEX
    Explanations

    seeking ban or stay

    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
     ڤ
    -0.79
    Vox
    -0.77
    emptyset
    -0.76
    UINTN
    -0.73
     DBNull
    -0.73
    ánicos
    -0.71
    izient
    -0.71
     will
    -0.71
    togen
    -0.71
    posis
    -0.71
    POSITIVE LOGITS
    入れて
    0.88
     uniform
    0.86
    Uniform
    0.84
    zerne
    0.80
     utwor
    0.80
     culprits
    0.80
    uniform
    0.80
     Uniform
    0.78
     Brugge
    0.75
     grant
    0.75
    Activations Density 0.021%

    No Known Activations