© 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. 119115
    Prev
    Next
    INDEX
    Explanations

    programming code and file paths

    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
    скай
    -0.77
    rng
    -0.76
     Gay
    -0.72
    yoto
    -0.70
    setPref
    -0.69
    NLS
    -0.69
     direct
    -0.68
     certified
    -0.68
    kunt
    -0.68
     ISSUES
    -0.68
    POSITIVE LOGITS
    곱
    0.77
    quarto
    0.75
    сков
    0.65
    telemetry
    0.64
    textfield
    0.63
     sewed
    0.61
    кот
    0.60
    aos
    0.60
     insuring
    0.60
    照
    0.59
    Activations Density 0.089%

    No Known Activations