© 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. 41-GEMMASCOPE-2-RES-262K
    7. 22962
    Prev
    Next
    INDEX
    Explanations

    interjections and introductory adverbs

    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_all/layer_41_width_262k_l0_big
    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
    ✅
    0.40
     aktivit
    0.39
     específicamente
    0.38
    为了
    0.37
     koncent
    0.37
     calming
    0.37
    ႃ
    0.37
     shēng
    0.36
    કમાં
    0.36
    .]
    0.36
    POSITIVE LOGITS
    Incidentally
    0.68
     Incidentally
    0.66
     oh
    0.63
    Oh
    0.61
     Frankly
    0.59
     Oh
    0.59
    Isn
    0.58
    Honestly
    0.52
    And
    0.52
     übrigens
    0.50
    Activations Density 0.000%

    No Known Activations