© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 51718
    Prev
    Next
    INDEX
    Explanations

    avoid sexual acts

    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
    клика
    0.50
    ará
    0.49
    i
    0.47
    oses
    0.45
     istri
    0.45
    arza
    0.44
    ارا
    0.44
    διο
    0.43
    ખ્યા
    0.43
    akat
    0.43
    POSITIVE LOGITS
    North
    0.45
    শাহ
    0.45
    Secret
    0.44
     तत्
    0.42
    Spain
    0.42
     ศ
    0.42
    Naissance
    0.42
    thorpe
    0.41
     سف
    0.41
    Germany
    0.40
    Activations Density 0.031%

    No Known Activations