© 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-16K
    7. 13517
    Prev
    Next
    INDEX
    Explanations

    explanatory phrases

    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_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
    gestion
    0.41
    🖉
    0.39
     عامر
    0.38
    verify
    0.38
     gunfire
    0.38
     проверки
    0.37
    қу
    0.37
    Étienne
    0.37
    靔
    0.36
     américains
    0.36
    POSITIVE LOGITS
    ……..
    0.42
    …..
    0.41
     ….
    0.40
    ….
    0.38
    ･･･
    0.38
    дування
    0.38
    ・・・・
    0.37
    说什么
    0.37
     …..
    0.36
     ....
    0.36
    Activations Density 0.173%

    No Known Activations