© 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. 129019
    Prev
    Next
    INDEX
    Explanations

    negative emotional states

    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
     and
    -1.55
    Why
    -1.45
     +
    -1.38
     entweder
    -1.31
     Things
    -1.31
    What
    -1.28
     probabilmente
    -1.24
     extérieures
    -1.24
     =
    -1.22
    un
    -1.21
    POSITIVE LOGITS
     further
    1.29
     Consejos
    1.27
     كات
    1.26
     bordada
    1.24
     then
    1.22
     ناش
    1.19
     if
    1.18
     betul
    1.18
     entire
    1.17
    Voiced
    1.17
    Activations Density 0.052%

    No Known Activations