© 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. 118974
    Prev
    Next
    INDEX
    Explanations

    C# generics

    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
     vastly
    -1.09
    atam
    -0.92
    ᵊ
    -0.90
    hiel
    -0.85
    sometimes
    -0.84
    ULLY
    -0.84
     revamped
    -0.83
    给
    -0.83
    TOO
    -0.82
    owali
    -0.80
    POSITIVE LOGITS
     eleven
    0.94
     for
    0.89
     after
    0.86
     cortes
    0.85
     fifteen
    0.84
     twelve
    0.82
     fourteen
    0.82
     krav
    0.81
     sadar
    0.81
    Cor
    0.80
    Activations Density 0.001%

    No Known Activations