© 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. 1192
    Prev
    Next
    INDEX
    Explanations

    article and noun

    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
    ﯼ
    1.59
    ially
    1.58
     पूर्ण
    1.50
    你
    1.48
    ının
    1.43
     beatae
    1.43
    ала
    1.43
    ения
    1.43
    ifiable
    1.42
    А
    1.42
    POSITIVE LOGITS
     εξε
    1.52
    時点で
    1.48
     ruck
    1.48
    騒
    1.48
    ppsala
    1.46
     Shit
    1.45
     Ness
    1.40
    la
    1.38
    rock
    1.36
     тяжё
    1.36
    Activations Density 0.175%

    No Known Activations