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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11344
    Prev
    Next
    INDEX
    Explanations

    void((

    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
     that
    -1.07
    。「
    -1.03
     even
    -1.02
     provide
    -1.02
     another
    -1.01
     just
    -0.98
     one
    -0.97
     to
    -0.96
     of
    -0.96
     "
    -0.96
    POSITIVE LOGITS
    是一位
    1.18
     soñar
    1.17
     SUCH
    1.16
     astfel
    1.13
     sikker
    1.09
     inalámb
    1.08
     klanten
    1.04
     lác
    1.04
     påvir
    1.04
     cuarzo
    1.02
    Activations Density 0.010%

    No Known Activations