© 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. 74760
    Prev
    Next
    INDEX
    Explanations

    switchMap operator

    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
    夘
    -1.92
    ↵
    -1.91
     podremos
    -1.89
    ྥ
    -1.86
     також
    -1.80
     nouvelles
    -1.69
    觊
    -1.60
    鲔
    -1.60
     
    -1.59
     (?
    -1.56
    POSITIVE LOGITS
     this
    1.80
     endforeach
    1.75
    榈
    1.73
    ꪹ
    1.73
    𝘆
    1.72
     on
    1.69
    鲧
    1.69
    which
    1.68
    xiv
    1.65
    änemark
    1.61
    Activations Density 0.015%

    No Known Activations