© 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. 24758
    Prev
    Next
    INDEX
    Explanations

    at university

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

    causing harm or suffering

    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
     Expertise
    0.48
     فِي
    0.43
     Certification
    0.42
     الاستاذ
    0.41
    ā
    0.41
    </h3>
    0.41
    :
    0.41
    İŞ
    0.41
    us
    0.40
     Practice
    0.40
    POSITIVE LOGITS
     drifts
    0.52
     extract
    0.46
    那我們
    0.45
     condense
    0.44
     accumulate
    0.44
     cultiv
    0.43
     Vázquez
    0.42
     กล
    0.42
     immers
    0.41
     immerse
    0.41
    Activations Density 0.000%

    No Known Activations