© 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. 72992
    Prev
    Next
    INDEX
    Explanations

    stabilization

    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
     But
    -2.77
    schermata
    -2.58
     แต่
    -2.44
    ࿙
    -2.36
     peculiar
    -2.25
     entreg
    -2.23
     The
    -2.22
     había
    -2.20
     neust
    -2.20
     Of
    -2.19
    POSITIVE LOGITS
    bbling
    2.64
    </strong>
    2.63
    by
    2.56
    p
    2.33
    ially
    2.33
    itizing
    2.31
    ín
    2.22
    蓥
    2.20
    up
    2.20
    ised
    2.19
    Activations Density 0.008%

    No Known Activations