© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7075
    Prev
    Next
    INDEX
    Explanations

    words starting with "che"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    न
    1.14
    descriptors
    0.96
    ЛЕ
    0.91
     Εκ
    0.90
    ل
    0.90
    শান
    0.89
    igil
    0.89
    сыз
    0.88
    ट
    0.87
    ɦ
    0.85
    POSITIVE LOGITS
    tty
    0.98
    yenne
    0.90
    стно
    0.90
    ATING
    0.90
    ovno
    0.89
    ᱫ
    0.89
    ltu
    0.89
    byshev
    0.88
    ധ്യമ
    0.87
     jár
    0.87
    Activations Density 0.068%

    No Known Activations