© 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-16K
    7. 2551
    Prev
    Next
    INDEX
    Explanations

    sexual exploitation, abuse, or endangerment

    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_16k_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
    拒绝
    0.37
     Donations
    0.34
    衾
    0.34
    Alternatives
    0.34
     אות
    0.33
    Insurance
    0.33
    ắn
    0.32
    elés
    0.32
    舧
    0.32
     Insurance
    0.32
    POSITIVE LOGITS
     highly
    0.46
     extremely
    0.45
    highly
    0.45
     dehuman
    0.44
     экстре
    0.43
     precarious
    0.42
     extremadamente
    0.42
     violence
    0.42
    promotion
    0.42
    extré
    0.41
    Activations Density 0.909%

    No Known Activations