© 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. 13-GEMMASCOPE-2-RES-16K
    7. 1891
    Prev
    Next
    INDEX
    Explanations

    please call

    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
     развитие
    1.30
    encement
    1.24
    이란
    1.24
    -_
    1.21
    ған
    1.19
    이라는
    1.18
    ുകളുടെ
    1.16
    ㎜
    1.15
    ロジー
    1.14
    так
    1.12
    POSITIVE LOGITS
     liable
    1.53
     looking
    1.46
     integrable
    1.44
     drunk
    1.42
     ashamed
    1.41
     addicted
    1.39
     aware
    1.38
     prone
    1.38
     guilty
    1.36
     roomy
    1.35
    Activations Density 0.617%

    No Known Activations