© 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. 157850
    Prev
    Next
    INDEX
    Explanations

    governance, Ammonium, soya, cabbage

    np_acts-logits-general · gemini-2.5-flash-lite

    miniature, aurora, recently graduated

    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
    st
    0.68
    m
    0.57
    w
    0.53
    中
    0.50
    ｔ
    0.48
    म
    0.48
    jad
    0.48
    ד
    0.47
    ｓ
    0.46
    ats
    0.46
    POSITIVE LOGITS
     governance
    0.55
     Ammonium
    0.52
     soya
    0.50
     carriage
    0.50
     ставки
    0.49
    払い
    0.49
     гли
    0.48
     fasci
    0.48
     cabbage
    0.48
     ग्ले
    0.48
    Activations Density 0.001%

    No Known Activations