© 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. 119315
    Prev
    Next
    INDEX
    Explanations

    self-related actions or descriptions

    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
     who
    -0.78
    లా
    -0.76
     jakości
    -0.70
    }=-\
    -0.68
    vcpu
    -0.68
    LT
    -0.68
     $=
    -0.68
     January
    -0.67
     notwendig
    -0.67
    vscode
    -0.67
    POSITIVE LOGITS
     acclaimed
    0.79
     Goals
    0.75
     Styles
    0.75
    🚲
    0.73
    WithFormat
    0.73
    細かく
    0.73
    🧜
    0.71
    Coordinate
    0.71
    goals
    0.71
    üstung
    0.69
    Activations Density 0.025%

    No Known Activations