© 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. 85894
    Prev
    Next
    INDEX
    Explanations

    Linux, Ford, List, matches

    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
    ']
    -1.59
    こんばん
    -1.58
    ₄
    -1.55
     alltid
    -1.55
     tanken
    -1.53
     it
    -1.48
     dieren
    -1.48
     programmet
    -1.47
    ●●
    -1.45
     bekym
    -1.45
    POSITIVE LOGITS
     where
    2.03
     same
    1.63
     but
    1.59
     search
    1.54
     answer
    1.54
     after
    1.47
    for
    1.41
    where
    1.41
     одной
    1.38
     by
    1.34
    Activations Density 0.030%

    No Known Activations