© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 14586
    Prev
    Next
    INDEX
    Explanations

    planning suicide

    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/layer_31_width_65k_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
    Чу
    0.49
    buildCommand
    0.48
    leqslant
    0.47
    น้อย
    0.47
    隂
    0.46
     तपास
    0.44
     صفحۀ
    0.44
     иллюстрация
    0.44
     partícula
    0.44
    审核
    0.43
    POSITIVE LOGITS
     always
    0.57
     AC
    0.45
     resigned
    0.44
     silver
    0.44
     programmatic
    0.43
     never
    0.43
     membership
    0.43
    always
    0.43
    0
    0.43
     audience
    0.42
    Activations Density 0.003%

    No Known Activations