© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93073
    Prev
    Next
    INDEX
    Explanations

    license and 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
     get
    -1.51
     tells
    -1.37
     tell
    -1.34
     even
    -1.34
     have
    -1.33
     want
    -1.33
     find
    -1.32
     time
    -1.30
     gives
    -1.30
     bring
    -1.26
    POSITIVE LOGITS
    这般
    1.56
     ざ
    1.38
     épices
    1.33
    küche
    1.30
    felf
    1.30
     acepción
    1.25
    ̵
    1.23
     intrigu
    1.21
     pertanto
    1.20
    forderungen
    1.19
    Activations Density 0.002%

    No Known Activations