© 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. 74346
    Prev
    Next
    INDEX
    Explanations

    filler and spacer

    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
    
    -1.60
     deniz
    -1.49
     符号
    -1.48
    鯡
    -1.44
     persönlich
    -1.41
     сделал
    -1.41
     avesse
    -1.38
    engertian
    -1.38
     strangle
    -1.35
    iscono
    -1.34
    POSITIVE LOGITS
    5
    1.48
     filler
    1.47
     Fill
    1.47
     $\
    1.40
     I
    1.34
        
    1.33
     uncovered
    1.32
     */}
    1.29
    在我
    1.29
    に出演
    1.25
    Activations Density 0.029%

    No Known Activations