© 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. 50118
    Prev
    Next
    INDEX
    Explanations

    created by or modify

    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
    av
    -0.74
    LL
    -0.71
     As
    -0.71
    we
    -0.71
     infamous
    -0.70
    value
    -0.69
    As
    -0.69
     ten
    -0.68
     tę
    -0.67
     twelve
    -0.66
    POSITIVE LOGITS
     ۱۵
    0.75
     野
    0.72
     fifteenth
    0.72
     Fifteen
    0.71
    劇場
    0.70
     soeur
    0.69
    urende
    0.68
    eby
    0.67
    Andrews
    0.67
     HUM
    0.66
    Activations Density 0.436%

    No Known Activations