© 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. 10-GEMMASCOPE-RES-131K
    4. 124735
    Prev
    Next
    INDEX
    Explanations

    static

    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
     the
    -1.63
     bugün
    -1.44
     a
    -1.42
     birçok
    -1.40
     reflexiones
    -1.38
     ciddi
    -1.35
     of
    -1.34
     yeterli
    -1.31
     moeten
    -1.30
     nyní
    -1.30
    POSITIVE LOGITS
    This
    1.42
    when
    1.34
     istan
    1.34
     tzu
    1.34
     bosco
    1.33
    Because
    1.25
    this
    1.24
     maso
    1.23
    Two
    1.23
     puo
    1.22
    Activations Density 0.016%

    No Known Activations