© 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. 101039
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    льный
    0.47
    base
    0.44
    フト
    0.43
    霎
    0.43
    не
    0.42
    Base
    0.42
    قطه
    0.42
    מה
    0.42
     dettaglio
    0.42
    マ
    0.42
    POSITIVE LOGITS
     prób
    0.54
     négoci
    0.47
     raczej
    0.45
     także
    0.45
     również
    0.45
     kleinere
    0.45
     också
    0.44
     også
    0.43
     Hölder
    0.43
     Bakan
    0.43
    Activations Density 0.004%

    No Known Activations