© 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. 110990
    Prev
    Next
    INDEX
    Explanations

    Niger

    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
     McLeod
    -0.82
     能
    -0.77
    gendes
    -0.75
    variant
    -0.74
     местах
    -0.73
    华为
    -0.72
    ükemmel
    -0.72
     tæ
    -0.72
    GENERIC
    -0.71
    Mc
    -0.71
    POSITIVE LOGITS
     Niger
    1.65
    Niger
    1.44
     niger
    0.91
     uranium
    0.91
    niger
    0.91
     Kroger
    0.86
     Snyder
    0.83
     nig
    0.82
    nyder
    0.82
     NIGER
    0.78
    Activations Density 0.011%

    No Known Activations