© 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. 40536
    Prev
    Next
    INDEX
    Explanations

    XI, Camilla, dipole

    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
     itſelf
    -2.69
    涐
    -2.64
    Ruju
    -2.58
    骘
    -2.53
     cromo
    -2.52
    
    -2.47
    肫
    -2.47
    warnai
    -2.44
     pneu
    -2.41
     barbacoa
    -2.39
    POSITIVE LOGITS
    on
    3.06
    "
    2.97
     he
    2.89
    u
    2.73
     porque
    2.58
     وم
    2.53
    1
    2.52
    8
    2.44
    and
    2.39
    te
    2.36
    Activations Density 0.003%

    No Known Activations