© 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. 22-GEMMASCOPE-RES-131K
    7. 71549
    Prev
    Next
    INDEX
    Explanations

    technical and scientific 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_22/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
     itself
    -0.84
    atize
    -0.81
    gungen
    -0.81
     конкре
    -0.76
     Kij
    -0.75
    μα
    -0.74
    onatos
    -0.73
    瘻
    -0.73
     soci
    -0.72
     cuis
    -0.71
    POSITIVE LOGITS
     another
    0.89
     másik
    0.84
    別の
    0.82
    Secure
    0.82
    尷
    0.81
     Наталья
    0.78
    Xi
    0.75
     כשה
    0.74
    矚
    0.73
    Second
    0.72
    Activations Density 0.135%

    No Known Activations