© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110538
    Prev
    Next
    INDEX
    Explanations

    numbers and code snippets

    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
     Lew
    -0.82
    want
    -0.74
     Владими
    -0.71
    pty
    -0.69
    mig
    -0.69
     exploración
    -0.68
     prayer
    -0.68
    enjoy
    -0.68
    тя
    -0.67
    nstein
    -0.67
    POSITIVE LOGITS
     Resolver
    0.69
    Hughes
    0.69
     leftist
    0.66
    ehr
    0.64
     spirits
    0.63
    podium
    0.63
    LEFT
    0.61
     highlighting
    0.60
     الصحية
    0.60
    絶
    0.60
    Activations Density 0.080%

    No Known Activations