© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2419
    Prev
    Next
    INDEX
    Explanations

    stating and indicating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     объявления
    1.81
     Console
    1.78
    डमी
    1.78
     серви
    1.78
    آ
    1.76
    цы
    1.71
    jež
    1.71
    бри
    1.71
    пански
    1.70
    ריה
    1.70
    POSITIVE LOGITS
     amorphous
    1.57
     για
    1.54
     "-
    1.53
     abnormally
    1.52
     exponentially
    1.50
     occurs
    1.48
    "/
    1.44
     ("
    1.43
     gradual
    1.42
     fon
    1.42
    Activations Density 0.245%

    No Known Activations