© 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. 41159
    Prev
    Next
    INDEX
    Explanations

    bleeding, bloodshed, hemorrhage

    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
    م
    1.12
    нде
    1.03
    لي
    1.02
    بول
    1.00
    ی
    0.99
    ações
    0.98
    تها
    0.97
     ఆఫ్
    0.95
     πολ
    0.93
    ныя
    0.93
    POSITIVE LOGITS
     bloody
    1.41
     bloodshed
    1.27
     bleeding
    1.20
    ot
    1.10
    出血
    1.10
     bleed
    1.08
     conference
    1.05
     cardiology
    0.97
    痔
    0.96
    ut
    0.95
    Activations Density 0.019%

    No Known Activations