© 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. 57437
    Prev
    Next
    INDEX
    Explanations

    sharing caring giving

    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
     meso
    -0.78
     terá
    -0.75
    wish
    -0.73
     мульт
    -0.71
    progress
    -0.69
    lié
    -0.68
     окна
    -0.66
     realizar
    -0.66
     Mikhail
    -0.66
     tercih
    -0.66
    POSITIVE LOGITS
     caring
    1.23
     Caring
    1.06
     sharing
    0.99
     Sharing
    0.95
    Caring
    0.91
    caring
    0.88
    jillo
    0.76
    sharing
    0.75
    Sharing
    0.74
     formulae
    0.72
    Activations Density 0.050%

    No Known Activations