© 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-65K
    7. 1726
    Prev
    Next
    INDEX
    Explanations

    digits 5 and 7

    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_65k_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
    二十
    0.50
    三十
    0.50
     */
    0.45
    四个
    0.44
     čty
    0.44
     बारह
    0.44
     arrays
    0.43
    Two
    0.43
    Thirty
    0.42
     Two
    0.41
    POSITIVE LOGITS
    isomer
    0.58
     terras
    0.57
    酶
    0.55
     त्यौहार
    0.54
    ídio
    0.54
    affinity
    0.54
    aVal
    0.54
     Тео
    0.53
    Descripcion
    0.53
     хозя
    0.53
    Activations Density 0.006%

    No Known Activations