© 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. 58018
    Prev
    Next
    INDEX
    Explanations

    events before or after disruptions

    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
     went
    0.47
    went
    0.41
     Went
    0.39
     শ্রেণী
    0.38
     పాల్గొన్నారు
    0.38
     gick
    0.37
     obtenue
    0.37
    ("-"*
    0.37
    においては
    0.36
     શબ્
    0.36
    POSITIVE LOGITS
     amid
    0.69
     despite
    0.68
     amidst
    0.66
     but
    0.65
     says
    0.63
    says
    0.62
    amid
    0.59
    Says
    0.54
     warns
    0.52
     Says
    0.52
    Activations Density 0.001%

    No Known Activations