© 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. 3389
    Prev
    Next
    INDEX
    Explanations

    ecological concepts and Ukraine

    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
    ть
    2.79
    SCAPE
    2.65
    zhen
    2.61
     toc
    2.38
    ็ว
    2.29
     ..
    2.29
    ಾ
    2.25
    ็จ
    2.25
     coop
    2.24
     .
    2.24
    POSITIVE LOGITS
    nya
    4.43
    了
    3.98
    다면
    3.60
    ly
    3.59
    다고
    3.33
    ই
    3.24
    서
    3.16
    ský
    3.13
    nt
    3.09
    smöglichkeiten
    3.04
    Activations Density 0.001%

    No Known Activations