© 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. 92373
    Prev
    Next
    INDEX
    Explanations

    code, errors, or lists

    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
    Upp
    -0.75
     povin
    -0.74
    natives
    -0.71
    gore
    -0.68
    upe
    -0.67
     Sessions
    -0.66
    copies
    -0.65
     kirj
    -0.63
     foregoing
    -0.63
     Sov
    -0.63
    POSITIVE LOGITS
     anchors
    0.72
    CURSOR
    0.68
     ماده
    0.65
     Oversight
    0.64
    ilija
    0.63
     karaoke
    0.63
     collar
    0.63
    linearGradient
    0.62
    бит
    0.62
    attr
    0.62
    Activations Density 0.060%

    No Known Activations