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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 3905
    Prev
    Next
    INDEX
    Explanations

    polycarbonate shell and filter

    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
    </h5>
    -1.54
    e
    -1.52
     बेह
    -1.50
    limited
    -1.48
     Inference
    -1.48
    ا
    -1.45
    _
    -1.44
    bad
    -1.42
     using
    -1.38
    d
    -1.38
    POSITIVE LOGITS
    轳
    2.11
     wszystkie
    1.63
    }$,
    1.55
    NTIS
    1.50
     Կ
    1.50
    ウド
    1.47
    dersfield
    1.47
     than
    1.47
    
    1.46
    
    1.45
    Activations Density 0.038%

    No Known Activations