© 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. 42017
    Prev
    Next
    INDEX
    Explanations

    May

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

    categories and practical importance

    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
     hallmarks
    0.47
    ac
    0.46
     Republik
    0.46
    zon
    0.46
     na
    0.44
     prolifer
    0.43
     на
    0.43
     “
    0.42
     для
    0.42
    т
    0.41
    POSITIVE LOGITS
     découvert
    0.51
    酲
    0.48
    നിക്ക്
    0.47
    正则表达式
    0.46
     commencent
    0.46
    然后再
    0.45
     อย่า
    0.44
    图中
    0.44
     énorm
    0.44
    මි
    0.43
    Activations Density 0.000%

    No Known Activations