© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11333
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and variables

    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
     leur
    -1.07
     leurs
    -1.02
     nji
    -0.96
     их
    -0.96
     reiz
    -0.89
    NRAS
    -0.88
    ortheast
    -0.86
     entonces
    -0.85
    ítez
    -0.85
     etap
    -0.84
    POSITIVE LOGITS
     both
    1.23
     already
    1.16
     our
    1.13
     your
    1.05
     Problemen
    0.99
     those
    0.94
    サキ
    0.94
    我們的
    0.92
    زوج
    0.91
     Olivenöl
    0.90
    Activations Density 0.018%

    No Known Activations