© 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. 128487
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

    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
     both
    -1.64
     more
    -1.25
     started
    -1.23
     starts
    -1.23
     first
    -1.22
     begin
    -1.22
     most
    -1.19
     being
    -1.18
     all
    -1.16
     having
    -1.16
    POSITIVE LOGITS
     maniere
    1.39
     unie
    1.25
     vó
    1.22
     boister
    1.20
    phylococcus
    1.20
     perioden
    1.19
     brune
    1.18
     البرنامج
    1.18
    haling
    1.14
     смотрите
    1.14
    Activations Density 0.053%

    No Known Activations