© 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. 222673
    Prev
    Next
    INDEX
    Explanations

    diverse words and languages

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

    occasional to infrequent events

    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
     an
    0.46
     combustible
    0.44
    이지만
    0.44
    يج
    0.42
    M
    0.41
     BUT
    0.41
     merchandise
    0.40
    W
    0.40
    C
    0.39
     than
    0.39
    POSITIVE LOGITS
     کافی
    0.56
    心态
    0.48
    偶尔
    0.48
     děti
    0.46
    klore
    0.44
     బోర్
    0.44
    Transicao
    0.43
     ブラウン
    0.43
    ரிடம்
    0.43
     ذہنی
    0.42
    Activations Density 0.003%

    No Known Activations