© 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. 7-GEMMASCOPE-2-RES-16K
    7. 829
    Prev
    Next
    INDEX
    Explanations

    phrases starting with why

    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
    ו
    3.77
    ווי
    3.25
    𝓪
    3.13
    та
    3.05
    ل
    3.03
    ন
    2.98
    ς
    2.94
    ್
    2.93
    ्य
    2.85
    ש
    2.69
    POSITIVE LOGITS
    ged
    2.67
     tine
    2.60
    crib
    2.47
    rainian
    2.42
    gar
    2.41
    ឹម
    2.40
    ྤ
    2.36
    ?".
    2.33
     tle
    2.33
    ening
    2.22
    Activations Density 0.078%

    No Known Activations