© 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. 60931
    Prev
    Next
    INDEX
    Explanations

    front and rear locations

    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
    屨
    -1.61
    嚒
    -1.47
    瞜
    -1.37
    0
    -1.33
    蹓
    -1.32
     problemet
    -1.30
     inconnu
    -1.30
     corrupción
    -1.30
    Waar
    -1.25
     savait
    -1.25
    POSITIVE LOGITS
    —
    1.53
    にお
    1.43
     of
    1.41
    lahan
    1.41
    ’
    1.40
     three
    1.39
    しました
    1.39
     which
    1.36
     provides
    1.35
     suggests
    1.34
    Activations Density 0.009%

    No Known Activations