© 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. 55934
    Prev
    Next
    INDEX
    Explanations

    code snippets or annotations

    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
    }`}
    -0.76
    iol
    -0.75
    NUMBER
    -0.73
    ıt
    -0.73
     INC
    -0.71
    juje
    -0.71
    数组
    -0.71
    Consulting
    -0.70
    /******/
    -0.69
    Repost
    -0.68
    POSITIVE LOGITS
     занятия
    0.66
     caller
    0.65
    citename
    0.62
    Ŋ
    0.62
     Calls
    0.62
    儕
    0.61
     suppor
    0.61
     umfang
    0.60
     Snakes
    0.60
    Articulo
    0.60
    Activations Density 0.046%

    No Known Activations