© 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. 73402
    Prev
    Next
    INDEX
    Explanations

    Camille Norment, Allegations

    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
    There
    -3.19
    It
    -2.94
    ,
    -2.66
    5
    -2.64
     It
    -2.63
    7
    -2.61
    6
    -2.59
     ‘
    -2.58
    4
    -2.55
     There
    -2.45
    POSITIVE LOGITS
    趿
    2.70
    杙
    2.52
    儅
    2.27
    螣
    2.27
    ᨆ
    2.20
     batteri
    2.17
    神
    2.17
    鐽
    2.14
     geene
    2.11
    葶
    2.11
    Activations Density 0.001%

    No Known Activations