© 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. 10-GEMMASCOPE-RES-131K
    7. 41080
    Prev
    Next
    INDEX
    Explanations

    number followed by parenthesis

    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_10/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
     where
    -1.68
     in
    -1.46
    ījum
    -1.45
    omás
    -1.44
    uterte
    -1.41
     with
    -1.40
     from
    -1.39
     but
    -1.39
    żd
    -1.35
     verzorg
    -1.29
    POSITIVE LOGITS
    isierung
    1.61
     they
    1.53
    醅
    1.45
     sẽ
    1.39
    灩
    1.38
     encant
    1.36
    ↵↵
    1.34
     mindset
    1.33
    芋
    1.33
     você
    1.32
    Activations Density 0.003%

    No Known Activations