© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111024
    Prev
    Next
    INDEX
    Explanations

    special police or rescue teams

    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_10/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
    ggen
    -1.14
    jshint
    -1.13
     encendido
    -1.13
     podrás
    -1.10
    Emm
    -1.08
    ೫
    -1.07
     nació
    -1.06
    aimana
    -1.06
    opheles
    -1.06
     immemorial
    -1.03
    POSITIVE LOGITS
     and
    1.46
     it
    1.37
     viewed
    1.10
    %">
    1.09
    籥
    1.08
     situation
    1.04
     перио
    1.03
     be
    1.02
    ८
    1.02
    they
    1.01
    Activations Density 0.049%

    No Known Activations