© 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. 14687
    Prev
    Next
    INDEX
    Explanations

    tea and its types

    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
    3.42
    gios
    2.70
    znego
    2.58
    нном
    2.53
    د
    2.52
    o
    2.44
    zco
    2.41
    gery
    2.41
    dre
    2.41
    gende
    2.40
    POSITIVE LOGITS
    睬
    2.71
    ;\
    2.67
    oured
    2.64
    𝐲
    2.61
    $>$
    2.58
    ranger
    2.56
    ੫
    2.52
    ्य
    2.52
    ::_
    2.51
     [{\
    2.45
    Activations Density 0.008%

    No Known Activations