© 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. 10-GEMMASCOPE-RES-131K
    7. 44753
    Prev
    Next
    INDEX
    Explanations

    jankitude, Wankel, spank

    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
     Also
    -2.69
     Также
    -2.56
    kaç
    -2.41
     “
    -2.38
     Similarly
    -2.34
    ındaki
    -2.34
    
    -2.33
    használ
    -2.31
    astră
    -2.31
     either
    -2.30
    POSITIVE LOGITS
    c
    4.38
    ↵↵
    3.84
    s
    3.75
    p
    3.64
    D
    3.39
    2
    3.20
    E
    3.02
    which
    3.00
    k
    2.89
    X
    2.86
    Activations Density 0.014%

    No Known Activations