© 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. 102961
    Prev
    Next
    INDEX
    Explanations

    suicide or related concepts

    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
    তত্ব
    0.43
    Scaling
    0.41
     upl
    0.39
    Supports
    0.39
    㹂
    0.39
    क्की
    0.39
    sockets
    0.39
    ETHOD
    0.38
    垄
    0.38
    ্নের
    0.38
    POSITIVE LOGITS
     suicide
    2.23
     suicidal
    2.08
     suic
    2.05
     Suicide
    1.95
     suicides
    1.61
    自殺
    1.61
     आत्महत्या
    1.54
     আত্মহত্যা
    1.43
     kam
    1.11
     самоу
    0.98
    Activations Density 0.001%

    No Known Activations