© 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. 10-GEMMASCOPE-RES-131K
    7. 75171
    Prev
    Next
    INDEX
    Explanations

    graphic layer, product controller, touches moved

    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
    f
    -1.93
    m
    -1.76
    ed
    -1.67
    return
    -1.64
    p
    -1.63
    c
    -1.61
    b
    -1.58
    my
    -1.55
    u
    -1.55
    end
    -1.51
    POSITIVE LOGITS
    넋
    1.60
    xvi
    1.56
     madres
    1.52
    lxt
    1.48
     máme
    1.48
    playera
    1.47
     merece
    1.45
     that
    1.45
    chaleco
    1.45
     jį
    1.45
    Activations Density 0.045%

    No Known Activations