© 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. 67012
    Prev
    Next
    INDEX
    Explanations

    Taliban, Gestational, amygdala, Talmud

    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
    In
    -2.48
    At
    -2.44
    With
    -2.33
     They
    -2.22
     However
    -2.20
     With
    -2.13
    For
    -2.06
     The
    -2.06
     =
    -2.06
     ;
    -2.05
    POSITIVE LOGITS
    OUTUBE
    2.84
     抠
    2.50
    筇
    2.36
     faſt
    2.33
    硨
    2.28
    屄
    2.28
    𓆏
    2.22
    汌
    2.22
    鹛
    2.19
    鹪
    2.19
    Activations Density 0.003%

    No Known Activations