© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 488
    Prev
    Next
    INDEX
    Explanations

    words starting with letters

    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
    y
    1.25
    ו
    1.11
    u
    1.10
    in
    1.05
    a
    1.04
    ேட்
    1.01
    ോ
    1.01
    r
    1.00
    e
    0.96
     вя
    0.93
    POSITIVE LOGITS
    Ö
    1.38
    Ü
    1.33
    Ä
    1.32
    anganan
    1.28
    É
    1.26
    ukun
    1.22
    Ú
    1.21
    İ
    1.21
    ukan
    1.21
    ukk
    1.19
    Activations Density 0.988%

    No Known Activations