© 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. 3460
    Prev
    Next
    INDEX
    Explanations

    crafting and weaving styles

    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
    ges
    2.69
    чики
    2.49
    다는
    2.42
    чиков
    2.42
    чик
    2.39
     उतना
    2.37
    cijas
    2.36
    蒾
    2.34
    mios
    2.32
    ty
    2.32
    POSITIVE LOGITS
    ی
    3.15
    न
    3.07
     mắn
    2.88
    末
    2.87
    ing
    2.76
    yya
    2.71
    ে
    2.69
    ingar
    2.58
    lass
    2.57
    om
    2.56
    Activations Density 0.115%

    No Known Activations