© 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. 70247
    Prev
    Next
    INDEX
    Explanations

    relationship between

    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
    vensko
    -1.75
    出了一
    -1.57
    犄
    -1.54
    ifications
    -1.50
    了不少
    -1.48
    躂
    -1.45
    厛
    -1.44
     considérable
    -1.41
    ໊
    -1.34
    鉿
    -1.34
    POSITIVE LOGITS
    3
    1.95
     with
    1.81
    8
    1.55
     that
    1.53
    6
    1.44
    They
    1.40
    2
    1.38
     between
    1.36
     these
    1.35
    5
    1.31
    Activations Density 0.105%

    No Known Activations