© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 225619
    Prev
    Next
    INDEX
    Explanations

    action then its object or result

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     חש
    0.53
    𒃶
    0.50
    рія
    0.49
    ěstí
    0.47
     ឬ
    0.46
     trữ
    0.45
    iduría
    0.45
     základě
    0.45
     פּ
    0.45
    妫
    0.45
    POSITIVE LOGITS
     Children
    0.53
    Children
    0.48
     LWR
    0.48
     and
    0.47
     Speakers
    0.46
    മ
    0.46
     Gret
    0.46
    m
    0.46
    tien
    0.46
     Bik
    0.46
    Activations Density 0.001%

    No Known Activations