© 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. 62093
    Prev
    Next
    INDEX
    Explanations

    utility or action verbs

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

    finding or sourcing information

    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
    乐
    0.46
    TV
    0.45
    е
    0.45
    а
    0.44
    Lily
    0.43
    А
    0.43
    Ade
    0.43
    U
    0.43
    สวัสดี
    0.43
    cor
    0.42
    POSITIVE LOGITS
     weten
    0.50
     المعروف
    0.49
     ناج
    0.49
     بوص
    0.49
     xhrObj
    0.48
     النساء
    0.47
     عقد
    0.47
     जर्म
    0.47
     သိ
    0.47
     erricht
    0.45
    Activations Density 0.000%

    No Known Activations