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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107294
    Prev
    Next
    INDEX
    Explanations

    apache camel, U.S

    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
    ttp
    -0.75
    ZZZ
    -0.73
     Released
    -0.72
    oku
    -0.72
    क्षित
    -0.71
    stacle
    -0.71
     Kinetics
    -0.70
    ERAL
    -0.69
    OKU
    -0.69
     hilfreich
    -0.69
    POSITIVE LOGITS
    Dès
    0.78
     пото
    0.77
    Arquivo
    0.76
    hof
    0.75
     beste
    0.73
    nsec
    0.73
     θ
    0.73
    sies
    0.73
     polar
    0.72
     Rother
    0.71
    Activations Density 0.020%

    No Known Activations