© 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. 103897
    Prev
    Next
    INDEX
    Explanations

    out of the box

    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
    </strong>
    -1.50
     to
    -1.41
    ar
    -1.39
    amp
    -1.39
    <bos>
    -1.38
    毎月
    -1.37
     in
    -1.36
    at
    -1.31
    ave
    -1.30
    どのような
    -1.27
    POSITIVE LOGITS
    骝
    1.45
     plupart
    1.39
    ூர்
    1.38
     食堂
    1.38
     finos
    1.37
     orar
    1.35
     agricultores
    1.34
     seguras
    1.33
    cantara
    1.32
     शुर
    1.30
    Activations Density 0.036%

    No Known Activations