© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18739
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions

    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
    …?
    0.38
    வில்
    0.37
    …,
    0.36
    에서는
    0.35
     acaso
    0.35
    及び
    0.35
    ↵↵↵↵
    0.34
    斯
    0.34
     എന്നിവ
    0.34
     بأ
    0.34
    POSITIVE LOGITS
     என்றும்
    0.51
    െന്നും
    0.42
    」、
    0.41
    ”、
    0.39
     എന്നും
    0.39
     எனவும்
    0.38
     bạn
    0.38
     也
    0.38
    ⁣⁣
    0.37
     Bạn
    0.37
    Activations Density 0.411%

    No Known Activations