© 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. 10-GEMMASCOPE-RES-131K
    7. 73479
    Prev
    Next
    INDEX
    Explanations

    HTTP status codes

    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_10/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
     who
    -1.74
     always
    -1.51
     whose
    -1.43
    which
    -1.33
     chré
    -1.30
    meteries
    -1.30
     descubrió
    -1.24
     which
    -1.23
     resembles
    -1.20
     also
    -1.20
    POSITIVE LOGITS
    '>
    1.38
     beetje
    1.36
    mädchen
    1.30
    ↵
    1.30
     request
    1.29
     faſt
    1.23
    培训
    1.23
    tualmente
    1.22
    Pictures
    1.21
     negras
    1.20
    Activations Density 0.013%

    No Known Activations