© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11353
    Prev
    Next
    INDEX
    Explanations

    funny, key, best, common, understanding

    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_40_width_16k_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
    ла
    0.56
    מי
    0.50
    ൈ
    0.49
    пи
    0.46
    Основные
    0.46
    Donc
    0.45
    parte
    0.45
    ши
    0.44
    IIUM
    0.44
    н
    0.44
    POSITIVE LOGITS
     …
    0.46
     으로
    0.42
     Automotive
    0.42
     for
    0.41
     Illuminate
    0.41
     ’
    0.41
    伌
    0.41
     ….
    0.40
     Trader
    0.40
     Biography
    0.40
    Activations Density 0.287%

    No Known Activations