© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15730
    Prev
    Next
    INDEX
    Explanations

    under-19, under-17, U-14, U-18

    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
     époux
    -1.65
    ˂
    -1.63
     bénévol
    -1.59
     laiton
    -1.56
     """",
    -1.54
     égard
    -1.54
    
    -1.53
     '/':
    -1.49
     sû
    -1.46
     sué
    -1.46
    POSITIVE LOGITS
    2
    1.91
     these
    1.86
    5
    1.71
    8
    1.64
    7
    1.63
    3
    1.62
    ↵↵
    1.58
    了一些
    1.55
    N
    1.53
    F
    1.52
    Activations Density 0.027%

    No Known Activations