© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93652
    Prev
    Next
    INDEX
    Explanations

    numbers, code, and non-english 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
     chrétien
    -0.88
     chrétienne
    -0.74
     school
    -0.74
    ükü
    -0.74
     скоро
    -0.74
     carbone
    -0.73
     Cidade
    -0.73
     Halifax
    -0.72
    Cached
    -0.71
    ApiClient
    -0.71
    POSITIVE LOGITS
     nordrhein
    0.98
     unable
    0.91
     kennt
    0.90
    明るい
    0.83
     gợi
    0.82
    tubes
    0.80
    随着
    0.80
     новая
    0.79
     ẩm
    0.78
    隨著
    0.77
    Activations Density 0.000%

    No Known Activations