© 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. 47919
    Prev
    Next
    INDEX
    Explanations

    Pokemon, mythical creatures

    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
     Field
    -0.70
     Vitamin
    -0.69
     granular
    -0.69
     inoc
    -0.68
     Zum
    -0.68
     Tanaka
    -0.68
     pap
    -0.67
    Grad
    -0.67
    Charlie
    -0.66
     al
    -0.66
    POSITIVE LOGITS
    asinya
    0.86
     Mew
    0.85
     legislat
    0.82
    цом
    0.80
     mythical
    0.80
     Myth
    0.79
    Mew
    0.79
    forChild
    0.79
    🥑
    0.77
     Regu
    0.75
    Activations Density 0.012%

    No Known Activations