© 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. 231240
    Prev
    Next
    INDEX
    Explanations

    available, before, after

    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
    maat
    0.54
    Т
    0.53
    حی
    0.48
    دید
    0.46
    شی
    0.45
    داشت
    0.45
    ט
    0.45
    키
    0.45
    برای
    0.44
    skaya
    0.44
    POSITIVE LOGITS
    _{-}
    0.52
     губерна
    0.52
     ดิ
    0.52
     พิจิก
    0.52
     tỉnh
    0.51
     信
    0.50
     الخبر
    0.50
     அதிமுக
    0.48
     पिक्चर
    0.48
     hà
    0.48
    Activations Density 0.000%

    No Known Activations