© 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. 60667
    Prev
    Next
    INDEX
    Explanations

    AGAMOUS, ADS, SCM, Q:, A:, /*

    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
    ❭
    -0.82
    dani
    -0.73
    松山
    -0.71
     Dames
    -0.69
    lokasi
    -0.67
    Rohy
    -0.67
    }/${
    -0.66
    畴
    -0.65
    cules
    -0.65
    antism
    -0.64
    POSITIVE LOGITS
     speciation
    0.97
     activity
    0.85
     SIT
    0.85
     stepwise
    0.84
     NEA
    0.82
     hydrolysis
    0.81
    tador
    0.80
     Activity
    0.80
     Whitfield
    0.80
    activity
    0.79
    Activations Density 0.035%

    No Known Activations