© 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. 87175
    Prev
    Next
    INDEX
    Explanations

    questions about possibility

    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
    Breite
    -1.80
    ⚋
    -1.80
     USING
    -1.68
     conhecida
    -1.65
    行きたい
    -1.65
     установка
    -1.60
    に対する
    -1.57
     Increase
    -1.55
     JOHN
    -1.53
     UNDER
    -1.50
    POSITIVE LOGITS
     then
    1.89
     because
    1.88
     their
    1.79
     they
    1.67
     mainly
    1.60
     particularly
    1.56
     this
    1.55
     primarily
    1.51
    。(
    1.48
     there
    1.47
    Activations Density 0.123%

    No Known Activations