© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8264
    Prev
    Next
    INDEX
    Explanations

    initial reaction or blended colors

    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_13_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
    renched
    1.49
    quay
    1.43
    𝐪
    1.39
    angled
    1.37
    rapie
    1.32
    뀐
    1.31
    ghan
    1.30
    least
    1.29
    quels
    1.28
     COLLECTION
    1.28
    POSITIVE LOGITS
     ω
    1.34
    ω
    1.31
     spéc
    1.30
    উট
    1.27
    nö
    1.24
     exercício
    1.24
    Το
    1.21
     mehr
    1.21
    ت
    1.20
     také
    1.20
    Activations Density 0.000%

    No Known Activations