© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31956
    Prev
    Next
    INDEX
    Explanations

    conditional logic and exception handling

    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
     (
    -1.77
     but
    -1.64
     in
    -1.46
    providedIn
    -1.33
     to
    -1.30
     from
    -1.29
     søndag
    -1.23
     so
    -1.23
     first
    -1.19
     A
    -1.18
    POSITIVE LOGITS
    ↵
    1.76
     notwendigen
    1.28
    strukturen
    1.26
     arşivlendi
    1.23
    ेशा
    1.21
     koltuk
    1.21
    神
    1.21
     içeris
    1.20
     secado
    1.20
    SONY
    1.17
    Activations Density 0.022%

    No Known Activations