© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 416
    Prev
    Next
    INDEX
    Explanations

    Co/Cr/Gen and descent

    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
     stickers
    1.67
     Stickers
    1.55
     sticker
    1.53
     Word
    1.49
     прочита
    1.49
    <unused771>
    1.47
    <unused798>
    1.47
     getType
    1.46
     Trois
    1.45
     Dartmouth
    1.45
    POSITIVE LOGITS
    ة
    1.28
    ℎ
    1.22
    روں
    1.22
    e
    1.21
    시간
    1.20
     tempi
    1.17
    lumin
    1.17
    ोत्सव
    1.15
    cadilly
    1.14
    缓慢
    1.13
    Activations Density 0.000%

    No Known Activations