© 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. 27829
    Prev
    Next
    INDEX
    Explanations

    W-questions (who, what, when, where, why, how)

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

    abstract nouns and specific entities

    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
     belongs
    0.48
     toho
    0.48
    ieb
    0.46
     als
    0.45
     و
    0.45
     and
    0.45
     jako
    0.44
     ,
    0.44
       
    0.43
     is
    0.43
    POSITIVE LOGITS
    였다
    0.61
    受到了
    0.51
    Despatx
    0.50
    렸다
    0.50
    อังกฤษ
    0.47
    btnInventory
    0.47
     পারস্পরিক
    0.47
    냈다
    0.47
     имущества
    0.46
    语文
    0.46
    Activations Density 0.000%

    No Known Activations