© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130227
    Prev
    Next
    INDEX
    Explanations

    the surface or side

    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_22/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
     herbe
    -1.65
     maïs
    -1.63
     nimmer
    -1.58
     charmant
    -1.53
     mentale
    -1.52
    perative
    -1.46
     vertus
    -1.46
     rayures
    -1.40
     APPELL
    -1.40
    amazing
    -1.40
    POSITIVE LOGITS
     where
    1.75
     left
    1.41
     other
    1.28
     some
    1.27
     end
    1.20
     lower
    1.19
     each
    1.17
    t
    1.17
    :
    1.16
     either
    1.16
    Activations Density 0.047%

    No Known Activations