© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 2060
    Prev
    Next
    INDEX
    Explanations

    content describing rules or examples

    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
     Hadley
    1.54
     Correspondent
    1.27
    ळा
    1.22
     HO
    1.20
     Þ
    1.20
     correspondent
    1.15
     Cato
    1.14
     ï
    1.14
     газета
    1.13
     находиться
    1.13
    POSITIVE LOGITS
    sef
    1.55
    klar
    1.55
    hik
    1.52
    시다
    1.51
    bés
    1.47
    seur
    1.47
    ug
    1.45
    ക്ത
    1.43
    hya
    1.41
    ৎকার
    1.40
    Activations Density 0.000%

    No Known Activations