© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 119078
    Prev
    Next
    INDEX
    Explanations

    code identifiers

    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
     २
    -0.78
    幔
    -0.71
     anota
    -0.71
    drawRect
    -0.70
     bakteri
    -0.70
     aneh
    -0.69
    unset
    -0.68
     vä
    -0.68
     confiance
    -0.66
     Garner
    -0.66
    POSITIVE LOGITS
     fischer
    0.76
    liq
    0.73
     coyote
    0.69
     Highlight
    0.65
     hyg
    0.64
    夭
    0.63
    meri
    0.61
     Slide
    0.61
    blush
    0.61
     xer
    0.60
    Activations Density 0.106%

    No Known Activations