© 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. 251672
    Prev
    Next
    INDEX
    Explanations

    specific nouns followed by continuations

    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
     اکن
    0.54
    ністю
    0.51
    ກ
    0.50
    カイブ
    0.50
    濂
    0.50
    ისთვის
    0.49
    кал
    0.49
    蒨
    0.49
    ק
    0.49
    σα
    0.48
    POSITIVE LOGITS
     Bien
    0.48
     Judge
    0.48
     Year
    0.45
     trout
    0.45
     Buff
    0.45
     Vict
    0.44
     boll
    0.44
     Pils
    0.44
     Hur
    0.43
     urinal
    0.43
    Activations Density 0.001%

    No Known Activations