© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 3514
    Prev
    Next
    INDEX
    Explanations

    rain and its qualities

    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
    𝐥
    2.66
    hman
    2.57
    :///
    2.39
    lige
    2.26
    Falling
    2.25
    ↵↵↵↵↵↵↵↵↵↵
    2.24
    のは
    2.24
    Never
    2.20
    ক্ষেপ
    2.18
    agamo
    2.15
    POSITIVE LOGITS
    ోతి
    3.47
    лекет
    3.01
    ೋತಿ
    2.97
    imized
    2.88
    artment
    2.85
    فون
    2.84
    otros
    2.82
    ுகள்
    2.80
    𝒾
    2.80
    人民政府
    2.80
    Activations Density 0.171%

    No Known Activations