© 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. 23693
    Prev
    Next
    INDEX
    Explanations

    code, questions, dates, answers

    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
    𝒋
    -0.75
    stino
    -0.74
    rophore
    -0.72
    ᗷ
    -0.71
     megjelen
    -0.69
    nadier
    -0.69
    liegende
    -0.68
    彼らは
    -0.68
    Xem
    -0.68
    ทรง
    -0.68
    POSITIVE LOGITS
    medlem
    0.81
     comercial
    0.79
    ार्
    0.77
     algo
    0.77
    laş
    0.77
    堰
    0.77
    Tils
    0.76
    fled
    0.75
    .$
    0.74
    ահ
    0.74
    Activations Density 0.017%

    No Known Activations