© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129702
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

    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
    乄
    -2.61
    ные
    -2.59
     vous
    -2.55
     bús
    -2.45
    ⇿
    -2.39
     faux
    -2.30
     illicit
    -2.28
     Näch
    -2.28
     veía
    -2.28
     interrelated
    -2.25
    POSITIVE LOGITS
    '
    3.02
    O
    2.67
    {
    2.66
    M
    2.58
    *
    2.55
    硨
    2.48
     parfa
    2.45
    Ruju
    2.44
     marseille
    2.38
    <
    2.36
    Activations Density 0.010%

    No Known Activations