© 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. 16-GEMMASCOPE-2-RES-262K
    7. 88656
    Prev
    Next
    INDEX
    Explanations

    hairy vagina, poisonous plants, Arthur

    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_16_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
    й
    0.49
    ່ວນ
    0.47
    ¹)
    0.47
     ราศี
    0.46
    im
    0.45
    ЗО
    0.44
    ОР
    0.44
     polymerized
    0.44
     poter
    0.43
    ӓ
    0.43
    POSITIVE LOGITS
    cieron
    0.47
     nouveau
    0.45
    樓
    0.45
     nieuw
    0.44
     percentuale
    0.44
    centric
    0.44
     nouvelle
    0.43
     الانس
    0.43
    ⺊
    0.43
     নিরাপদ
    0.43
    Activations Density 0.000%

    No Known Activations