© 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. 67315
    Prev
    Next
    INDEX
    Explanations

    love, liking, enjoyment

    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
     of
    -1.70
     a
    -1.41
     this
    -1.40
     actualmente
    -1.34
     только
    -1.33
    rlrl
    -1.31
     bessere
    -1.23
     only
    -1.19
     now
    -1.19
     to
    -1.16
    POSITIVE LOGITS
     Colegio
    1.40
     Boletín
    1.23
     extraordin
    1.20
    рных
    1.20
    🐴
    1.18
    śnia
    1.16
    lets
    1.15
    谕
    1.14
    ECTOR
    1.13
    trieb
    1.11
    Activations Density 0.019%

    No Known Activations