© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 10502
    Prev
    Next
    INDEX
    Explanations

    tragic outcomes and negative events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    at
    2.22
    م
    2.09
    テナンス
    2.08
    म
    2.02
    де
    1.92
    ات
    1.90
     postérieur
    1.88
     discontent
    1.80
    ung
    1.80
    ان
    1.76
    POSITIVE LOGITS
    ни
    2.08
    y
    1.80
    tery
    1.80
    ków
    1.57
     ensue
    1.55
    yse
    1.54
    </tr>
    1.50
     DataFrame
    1.48
    kker
    1.48
    ي
    1.48
    Activations Density 0.007%

    No Known Activations