© 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. 93102
    Prev
    Next
    INDEX
    Explanations

    by someone or something

    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
     môžu
    -0.82
     hjälpa
    -0.82
     arbeta
    -0.80
     môžete
    -0.79
     ľah
    -0.77
     všetkých
    -0.76
     känna
    -0.76
     budete
    -0.75
     veľa
    -0.75
     Giugno
    -0.74
    POSITIVE LOGITS
     by
    4.50
     By
    1.86
    By
    1.84
    by
    1.73
    getBy
    1.41
     pelos
    1.40
    mby
    1.37
     BY
    1.35
    bys
    1.32
     getBy
    1.30
    Activations Density 0.018%

    No Known Activations