© 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. 13381
    Prev
    Next
    INDEX
    Explanations

    cup as ingredient measurement

    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
    iectasis
    2.92
    繹
    2.74
     $"
    2.70
    绎
    2.70
     டே
    2.66
     *"
    2.63
    expandindo
    2.63
     становништво
    2.59
     ônibus
    2.58
     nonexpansive
    2.58
    POSITIVE LOGITS
    لة
    2.69
    래
    2.29
    िक
    2.28
    دة
    2.27
    borough
    2.24
    rage
    2.14
    لال
    2.14
    arton
    2.13
    د
    2.12
    دت
    2.10
    Activations Density 0.011%

    No Known Activations