© 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. 2609
    Prev
    Next
    INDEX
    Explanations

    wikipedia entries

    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
     Leistungen
    2.44
     usług
    2.43
     kontek
    2.38
    Versioning
    2.30
     نتی
    2.24
     Publik
    2.23
     Políticas
    2.19
    최
    2.18
     Validación
    2.17
    แข่งขัน
    2.16
    POSITIVE LOGITS
    headed
    1.80
     bulb
    1.79
     protruding
    1.78
     bulbs
    1.77
    head
    1.76
     cloth
    1.75
     curling
    1.73
     strings
    1.71
    azolin
    1.65
     moon
    1.64
    Activations Density 0.741%

    No Known Activations