© 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. 15512
    Prev
    Next
    INDEX
    Explanations

    tournament rounds

    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
    已經
    -1.09
     nuovi
    -1.09
     largely
    -1.09
     alcune
    -1.07
     <
    -1.02
     garantiert
    -1.00
     already
    -0.99
     now
    -0.99
    usually
    -0.98
     alcuni
    -0.98
    POSITIVE LOGITS
     after
    1.26
     in
    1.09
     Benef
    1.06
     الوزن
    1.02
    Actors
    1.02
    entuk
    0.98
     kritik
    0.98
    遺産
    0.97
     brillant
    0.97
     terminating
    0.96
    Activations Density 0.026%

    No Known Activations