© 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. 78145
    Prev
    Next
    INDEX
    Explanations

    magnus uggla

    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
    驿
    -0.85
     å
    -0.79
    もう少し
    -0.73
     {}
    -0.72
     raken
    -0.69
     vanish
    -0.68
    嵯
    -0.68
    звичай
    -0.67
     radial
    -0.66
     ада
    -0.66
    POSITIVE LOGITS
     peanuts
    0.86
     dispozici
    0.79
     overlaps
    0.79
    newVal
    0.79
    ARTA
    0.78
    пка
    0.78
     MAF
    0.77
    ณา
    0.77
     overlapped
    0.77
     außerord
    0.77
    Activations Density 0.036%

    No Known Activations