© 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. 11445
    Prev
    Next
    INDEX
    Explanations

    models and reports

    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
    鸷
    -0.85
    ሓ
    -0.83
    ">${
    -0.82
    ଼
    -0.82
    ALLY
    -0.79
    落的
    -0.79
    Biblia
    -0.75
     вікі
    -0.75
     Req
    -0.75
    INDIAN
    -0.74
    POSITIVE LOGITS
     separate
    1.05
     another
    0.90
    separate
    0.88
     seperate
    0.79
     ansch
    0.79
     Then
    0.79
    ඝ
    0.79
    というのが
    0.77
     separately
    0.76
    Separate
    0.76
    Activations Density 0.106%

    No Known Activations