© 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. 12097
    Prev
    Next
    INDEX
    Explanations

    licensing conditions for redistributions

    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
    мян
    -0.75
    큘
    -0.72
    origen
    -0.71
     chaud
    -0.71
    Tol
    -0.71
     optik
    -0.70
     musik
    -0.70
     wandel
    -0.69
     Guar
    -0.69
    ropical
    -0.69
    POSITIVE LOGITS
     subsequ
    0.68
     biotin
    0.68
     дви
    0.66
     Pome
    0.63
    ല്ല
    0.63
     Điện
    0.63
    ertas
    0.63
     hyperplasia
    0.62
    اک
    0.62
    Pome
    0.61
    Activations Density 0.041%

    No Known Activations