© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27540
    Prev
    Next
    INDEX
    Explanations

    android and select lists

    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
     ausdrück
    -1.09
    得到的
    -1.03
     denselben
    -1.02
     demselben
    -1.02
     beitragen
    -1.00
     derselben
    -0.99
     unangemessene
    -0.97
     Только
    -0.97
     recebeu
    -0.96
    这句话
    -0.95
    POSITIVE LOGITS
     and
    1.34
    Çok
    1.05
    луйста
    1.05
     opar
    1.04
    IonicModule
    1.00
    İyi
    1.00
    trường
    0.99
    وقال
    0.98
    وكان
    0.97
     your
    0.96
    Activations Density 0.007%

    No Known Activations