© 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. 119636
    Prev
    Next
    INDEX
    Explanations

    Kurt, Q, Lap, various

    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
     Then
    -2.42
     biaya
    -2.38
     gustado
    -2.30
     originalen
    -2.25
     pengelola
    -2.25
     BRARY
    -2.23
    secutions
    -2.22
     giusti
    -2.22
     Frühjahr
    -2.20
     Vordergrund
    -2.19
    POSITIVE LOGITS
    that
    3.39
    <b>
    3.03
    s
    2.80
    there
    2.73
    or
    2.72
    <bos>
    2.53
    P
    2.44
    _
    2.38
    2
    2.36
    3
    2.25
    Activations Density 0.000%

    No Known Activations