© 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. 2620
    Prev
    Next
    INDEX
    Explanations

    19th century reference

    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
    at
    1.54
    <strong>
    1.52
    )(
    1.51
    iosk
    1.49
     campgrounds
    1.45
    학생
    1.44
     campground
    1.41
    ak
    1.41
    लाइट
    1.41
    (
    1.37
    POSITIVE LOGITS
    ..--..--
    2.11
     μαγγ
    2.10
    <unused1211>
    2.01
    PropertySheets
    2.00
    FhirExtension
    1.99
    ‏:‏
    1.96
    <unused724>
    1.95
     ちゃっ
    1.90
     έγινε
    1.89
    BinBuf
    1.87
    Activations Density 0.005%

    No Known Activations