© 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. 22-GEMMASCOPE-RES-131K
    7. 35736
    Prev
    Next
    INDEX
    Explanations

    campaign, language, testing, financing, client, money, Directive, effects

    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
    vcut
    -1.14
     verrou
    -1.10
     our
    -1.09
    lioni
    -1.05
    ocia
    -1.00
    漓
    -0.99
    stination
    -0.98
    inerario
    -0.95
    selor
    -0.94
    меты
    -0.93
    POSITIVE LOGITS
     bianche
    1.09
     denna
    1.02
     trono
    0.94
     presso
    0.91
     hiel
    0.90
     alha
    0.90
    ໝ
    0.88
     alun
    0.88
     lenge
    0.88
     this
    0.88
    Activations Density 0.173%

    No Known Activations