© 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. 2956
    Prev
    Next
    INDEX
    Explanations

    user activity

    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
    نوع
    2.26
    гү
    2.18
     AsRef
    2.12
    რი
    2.12
    <0x80>
    2.12
    ያንዳንዱ
    2.06
    ោគ
    2.05
    лье
    2.05
     tygod
    2.05
    uito
    2.04
    POSITIVE LOGITS
    یس
    2.18
    ிற்கும்
    2.11
     CRL
    2.05
    ில்
    2.04
    ന്തര
    2.02
    Periph
    2.00
    鹉
    2.00
     Priv
    1.98
    ולה
    1.97
     Secondary
    1.96
    Activations Density 0.155%

    No Known Activations