© 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. 72285
    Prev
    Next
    INDEX
    Explanations

    city team name pairs

    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
     first
    -1.37
     begin
    -1.29
     (
    -1.27
     on
    -1.25
     begins
    -1.22
     ännu
    -1.21
     for
    -1.19
     Unlike
    -1.18
     an
    -1.17
     after
    -1.17
    POSITIVE LOGITS
     stalwart
    1.55
     revamped
    1.44
    Descriere
    1.43
     Dinas
    1.40
     새
    1.38
     wacky
    1.36
    artment
    1.31
     nowy
    1.30
    妧
    1.27
    色んな
    1.26
    Activations Density 0.000%

    No Known Activations