© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 53957
    Prev
    Next
    INDEX
    Explanations

    notice and disclaimer

    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
    くださ
    -0.88
     Ejercicio
    -0.81
    violence
    -0.68
    Notific
    -0.68
    Ejercicio
    -0.66
    Bezier
    -0.65
    Prez
    -0.64
     noticeable
    -0.63
    Remain
    -0.63
     receding
    -0.61
    POSITIVE LOGITS
    theit
    0.75
    Acti
    0.75
    inari
    0.74
     Hebron
    0.73
    Cab
    0.73
    tween
    0.71
     blanks
    0.70
    azy
    0.69
    лих
    0.69
     سه
    0.69
    Activations Density 0.067%

    No Known Activations