© 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. 34-GEMMASCOPE-RES-131K
    7. 47429
    Prev
    Next
    INDEX
    Explanations

    sharing and sending

    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_34/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
     prič
    -0.82
    arbeit
    -0.81
    σύ
    -0.78
    坷
    -0.76
    setConfig
    -0.73
    UserInput
    -0.72
     Vorder
    -0.71
     tiếng
    -0.71
     mineral
    -0.71
    hma
    -0.70
    POSITIVE LOGITS
     Share
    1.20
    Share
    1.14
     share
    1.13
     SHARE
    1.07
    chooser
    1.04
    分享
    1.02
    share
    0.90
     friends
    0.90
     Send
    0.89
     sending
    0.83
    Activations Density 0.014%

    No Known Activations