© 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. 3557
    Prev
    Next
    INDEX
    Explanations

    purpose and operation

    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
    タリア
    1.61
     colors
    1.56
     stains
    1.54
     ബെ
    1.51
    埋
    1.50
     staining
    1.49
     لپ
    1.49
     편집
    1.48
     deal
    1.46
    élène
    1.46
    POSITIVE LOGITS
    arith
    2.26
    <unused1079>
    2.11
    рифмети
    2.06
    йма
    2.01
     alcun
    2.01
     quantas
    1.99
    uria
    1.93
    <unused1907>
    1.92
    苖
    1.91
    मति
    1.90
    Activations Density 0.017%

    No Known Activations