© 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. 22-GEMMASCOPE-RES-131K
    7. 72954
    Prev
    Next
    INDEX
    Explanations

    describing qualities after conjunctions

    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
    vább
    -1.55
    lorin
    -1.44
    ícias
    -1.41
    banez
    -1.38
    locene
    -1.32
     then
    -1.27
    딪
    -1.27
    foundland
    -1.26
     étage
    -1.25
     '\\;'
    -1.25
    POSITIVE LOGITS
     athletic
    1.38
     velha
    1.35
     able
    1.34
     approche
    1.29
     afraid
    1.27
     a
    1.22
     capaces
    1.20
     capable
    1.19
     patient
    1.17
     chré
    1.17
    Activations Density 0.021%

    No Known Activations