© 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. 37859
    Prev
    Next
    INDEX
    Explanations

    suicide, death, dying

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

    self-harm or suicide

    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
    diversity
    0.48
     разно
    0.47
     busier
    0.46
    mons
    0.46
     юбилей
    0.45
     आरआर
    0.45
    篱
    0.43
     актив
    0.43
    ඈ
    0.42
    active
    0.42
    POSITIVE LOGITS
     suicide
    1.20
     suicidal
    1.15
     suic
    1.12
     আত্মহত্যা
    1.05
    自殺
    1.05
     आत्महत्या
    1.02
    殉
    1.00
     martyrdom
    0.99
     Suicide
    0.97
     suicides
    0.94
    Activations Density 0.060%

    No Known Activations