© 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. 100165
    Prev
    Next
    INDEX
    Explanations

    positive evaluations

    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
     you
    -2.17
    même
    -2.16
     famoso
    -2.14
     delightfully
    -1.92
     célèbre
    -1.74
    よりも
    -1.73
     unbelievably
    -1.69
     ridiculously
    -1.68
     strikingly
    -1.67
    ⢅
    -1.65
    POSITIVE LOGITS
     first
    2.16
     took
    2.06
     went
    2.03
     one
    2.02
     could
    1.99
     showed
    1.95
     if
    1.95
     meticulous
    1.92
     lengthy
    1.90
     when
    1.87
    Activations Density 0.024%

    No Known Activations