© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4728
    Prev
    Next
    INDEX
    Explanations

    weakening power

    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
    ラ
    2.78
    や
    2.78
    レ
    2.73
    이
    2.70
    지
    2.61
     분
    2.59
    エ
    2.58
    な
    2.58
    す
    2.56
    비
    2.55
    POSITIVE LOGITS
     ל
    2.75
     ש
    2.45
     ק
    2.27
     ג
    2.23
     א
    2.22
     ב
    2.18
     ت
    2.12
     נ
    2.12
     ת
    2.05
     עד
    2.00
    Activations Density 0.002%

    No Known Activations