© 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. 34-GEMMASCOPE-RES-131K
    4. 90119
    Prev
    Next
    INDEX
    Explanations

    and how, when, why

    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_34/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
    鰱
    -1.27
     ↓,
    -1.20
    ...',
    -1.19
    stützung
    -1.19
    ième
    -1.19
     ſou
    -1.19
    tonsoft
    -1.18
     janu
    -1.17
     広場
    -1.17
    ۔
    -1.16
    POSITIVE LOGITS
     if
    1.56
     when
    1.42
     in
    1.31
     which
    1.26
     where
    1.26
     by
    1.26
     with
    1.26
     for
    1.22
     how
    1.20
     With
    1.20
    Activations Density 0.016%

    No Known Activations