© 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. 73668
    Prev
    Next
    INDEX
    Explanations

    code fragments and technical terms

    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
     facelift
    -0.77
    Kits
    -0.70
    ")}
    -0.70
    娌
    -0.69
     Kits
    -0.69
    )".
    -0.69
    yszcz
    -0.68
     Questi
    -0.68
     Oblivion
    -0.66
    𝙨
    -0.66
    POSITIVE LOGITS
    烃
    0.75
    ství
    0.75
    frontal
    0.74
    kaa
    0.72
    green
    0.68
     Unic
    0.68
    ondres
    0.67
     richness
    0.65
     competency
    0.65
     consequence
    0.64
    Activations Density 0.234%

    No Known Activations