© 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. 60766
    Prev
    Next
    INDEX
    Explanations

    code snippets 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
     Dynamic
    -0.71
    見えない
    -0.69
    Sequential
    -0.66
    UDAD
    -0.65
     над
    -0.64
     signing
    -0.63
    Dynamic
    -0.63
    DYNAMIC
    -0.63
    ̆
    -0.62
     jeste
    -0.62
    POSITIVE LOGITS
    ു
    0.72
    íses
    0.71
     ENT
    0.70
    魍
    0.69
    setdefault
    0.69
    rige
    0.69
     denomination
    0.68
     undervalued
    0.68
     Edith
    0.68
     Encounter
    0.68
    Activations Density 0.074%

    No Known Activations