© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82820
    Prev
    Next
    INDEX
    Explanations

    inflict harm or suffering

    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_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
    ждений
    0.49
    カイブ
    0.48
     absences
    0.48
     residuals
    0.48
     theorems
    0.47
    謊
    0.46
     biographies
    0.46
     transcripts
    0.45
     féidir
    0.45
    蛄
    0.45
    POSITIVE LOGITS
     Body
    0.48
    Base
    0.48
    base
    0.46
    Bar
    0.46
     Valley
    0.46
     ط
    0.45
     Just
    0.44
    Border
    0.44
    Valley
    0.44
     или
    0.43
    Activations Density 0.002%

    No Known Activations