© 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. 203095
    Prev
    Next
    INDEX
    Explanations

    victims of crimes or harm

    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
    Julie
    0.48
    ט
    0.47
    Nazi
    0.47
    י
    0.46
     ISIS
    0.45
    ISIS
    0.45
    ৌ
    0.43
    זי
    0.43
    ली
    0.42
    API
    0.42
    POSITIVE LOGITS
    tobs
    0.45
     nhưng
    0.45
     comunicação
    0.45
     तालुका
    0.44
    resión
    0.44
     yoki
    0.44
    egno
    0.43
     pertemuan
    0.43
     comunicazione
    0.42
     phố
    0.42
    Activations Density 0.001%

    No Known Activations