© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5554
    Prev
    Next
    INDEX
    Explanations

    parsing file lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
    insular
    1.41
    Cascade
    1.36
     Mitochondrial
    1.32
    Gruß
    1.32
    踱
    1.32
    Sorter
    1.31
    ázky
    1.25
    Aqua
    1.25
    abyrinth
    1.24
     anticancer
    1.23
    POSITIVE LOGITS
    ང་
    1.71
     ücret
    1.66
    داث
    1.63
     konse
    1.62
    STRUCT
    1.61
    ラル
    1.59
    第二天
    1.57
    బాద్
    1.57
    ོ
    1.57
     얼마
    1.56
    Activations Density 0.000%

    No Known Activations