© 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. 112870
    Prev
    Next
    INDEX
    Explanations

    Navajo postpartum jpeg Gulf

    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
    栒
    -3.52
    AdvEx
    -3.13
    鷓
    -3.05
    
    -2.92
    峮
    -2.88
    皛
    -2.84
    啬
    -2.84
    蹕
    -2.83
    湏
    -2.83
    豨
    -2.81
    POSITIVE LOGITS
     
    3.41
    We
    3.22
    —
    3.19
    In
    3.16
    e
    3.14
    To
    3.11
     Primarily
    2.91
     Pushing
    2.84
    ’
    2.72
    ter
    2.69
    Activations Density 0.010%

    No Known Activations