© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 9848
    Prev
    Next
    INDEX
    Explanations

    units of measurement and specific entities

    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_13_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
    マン
    1.59
    que
    1.57
    誕生
    1.56
     gayi
    1.55
     pronoun
    1.53
    削減
    1.53
    იან
    1.52
    ์
    1.50
    記録
    1.48
    yyum
    1.47
    POSITIVE LOGITS
    ไอ
    1.34
     ~
    1.29
    tt
    1.28
     Recognizing
    1.27
     ~.
    1.27
     Poultry
    1.25
    tl
    1.23
     Wings
    1.21
     Aquaculture
    1.19
     بواسطة
    1.17
    Activations Density 0.000%

    No Known Activations