© 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. 20117
    Prev
    Next
    INDEX
    Explanations

    strace, straddle, strabismus, strapon

    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
    '
    -3.08
     emporio
    -3.06
    ㈫
    -2.69
     GRATIS
    -2.55
     itſelf
    -2.39
     tapi
    -2.36
    .")
    -2.34
     nahil
    -2.31
    OOOOOOOO
    -2.30
    .’
    -2.28
    POSITIVE LOGITS
    聍
    3.13
     outrage
    3.09
    谵
    3.02
     inappropri
    2.72
    二代
    2.69
    宴会
    2.66
     aching
    2.61
     яке
    2.58
    三月
    2.53
     humble
    2.52
    Activations Density 0.005%

    No Known Activations