© 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. 65895
    Prev
    Next
    INDEX
    Explanations

    names starting with L followed by specific words

    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
     shared
    -0.78
     каждого
    -0.73
    shared
    -0.71
     Move
    -0.70
    чко
    -0.69
     pass
    -0.68
     move
    -0.68
    ams
    -0.68
    ὅ
    -0.67
    AMS
    -0.66
    POSITIVE LOGITS
    ngua
    0.79
    malıdır
    0.76
     detta
    0.75
     puto
    0.75
    ارية
    0.75
    برى
    0.75
    getYear
    0.74
    jate
    0.74
    xodo
    0.73
    کوراسیون
    0.71
    Activations Density 0.113%

    No Known Activations