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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14589
    Prev
    Next
    INDEX
    Explanations

    rating

    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
    𝐁
    3.35
    ౖ
    2.91
    ングラス
    2.82
    <unused2080>
    2.77
    asitriangular
    2.74
    iptic
    2.72
    蜍
    2.71
    𝐏
    2.68
     vial
    2.66
    जरीवाल
    2.63
    POSITIVE LOGITS
    c
    2.69
    i
    2.57
    ン
    2.55
    ratings
    2.43
    торов
    2.40
    rated
    2.31
     ’
    2.30
    y
    2.29
     ‘
    2.29
    犸
    2.28
    Activations Density 0.018%

    No Known Activations