© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91699
    Prev
    Next
    INDEX
    Explanations

    free software licenses can redistribute

    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
    eping
    -0.85
     пъ
    -0.79
    ('',
    -0.73
     châ
    -0.73
     supporto
    -0.72
    瘾
    -0.71
    에서
    -0.71
    utkan
    -0.70
    aye
    -0.70
     switch
    -0.69
    POSITIVE LOGITS
    boru
    0.85
    Australie
    0.79
    ++)
    0.78
    ねば
    0.77
    ForegroundColor
    0.75
    ++)
    0.75
     AppDelegate
    0.75
    ♏
    0.73
    neur
    0.73
    urons
    0.73
    Activations Density 0.328%

    No Known Activations