© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11564
    Prev
    Next
    INDEX
    Explanations

    initializer names

    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
    ять
    1.23
    >.</
    1.20
    ೇವ
    1.19
     틀
    1.18
    ẳn
    1.17
    ότη
    1.16
     Crear
    1.16
     Bex
    1.15
    က်
    1.14
    创建一个
    1.13
    POSITIVE LOGITS
     awakening
    1.48
     belated
    1.37
    遅
    1.34
    finally
    1.30
    delay
    1.28
     arriving
    1.27
     discoveries
    1.21
    albeit
    1.19
     slower
    1.18
     Awakening
    1.17
    Activations Density 0.199%

    No Known Activations