© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143487
    Prev
    Next
    INDEX
    Explanations

    Geographic locations and nationalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ،
    0.49
     ہمارے
    0.46
    ỡi
    0.45
    чество
    0.44
     insanely
    0.44
    issances
    0.43
    vindos
    0.43
     naprawdę
    0.42
     সিংহ
    0.42
    فاوت
    0.42
    POSITIVE LOGITS
    to
    0.58
     to
    0.51
     Beijing
    0.48
     Japan
    0.47
     it
    0.44
     J
    0.43
     Tokyo
    0.43
     see
    0.42
     Books
    0.42
     Japanese
    0.41
    Activations Density 0.000%

    No Known Activations