© 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. 12958
    Prev
    Next
    INDEX
    Explanations

    so-called, therefore, ordinarily

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

    explanation, definition, summary

    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
     ৩
    0.49
     UK
    0.48
     Montréal
    0.47
     ۴
    0.44
     MTL
    0.44
     ৬
    0.44
     NY
    0.43
     Montreal
    0.43
     ৪৫
    0.43
     ৪
    0.42
    POSITIVE LOGITS
    所謂
    0.64
    所谓
    0.59
     따라서
    0.51
    Therefore
    0.49
     sogenannten
    0.49
    akkhati
    0.46
     sogen
    0.46
     ordinairement
    0.45
     ስለዚህ
    0.45
     eksempel
    0.45
    Activations Density 0.037%

    No Known Activations