© 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. 74607
    Prev
    Next
    INDEX
    Explanations

    complaints about chargers, rights, or hours

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

    words causing offense

    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
     distribusi
    0.51
    ⤴
    0.48
     શેર
    0.46
     তারি
    0.46
     awalnya
    0.44
     ನಿ
    0.44
     [&
    0.44
    ♬
    0.43
     целью
    0.43
     défin
    0.42
    POSITIVE LOGITS
     offended
    0.54
     aggrieved
    0.50
     agitated
    0.50
     insulted
    0.48
     pissed
    0.48
     betrayed
    0.44
    oxid
    0.44
     irritated
    0.44
     brin
    0.43
     outraged
    0.42
    Activations Density 0.000%

    No Known Activations