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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3495
    Prev
    Next
    INDEX
    Explanations

    logic

    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
    𝒐
    3.18
    नैतिक
    2.76
    𝑬
    2.66
    𝙧
    2.65
    𝒊
    2.64
    रियो
    2.62
    حدیث
    2.60
    ientôt
    2.52
    ッケージ
    2.49
    𝒕
    2.47
    POSITIVE LOGITS
    ఠ
    2.57
    ttl
    2.47
    tten
    2.39
     \[
    2.29
    RAS
    2.29
     hing
    2.27
    申し上げ
    2.20
    kyt
    2.20
    ಢ
    2.19
    賴
    2.16
    Activations Density 0.111%

    No Known Activations