© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19637
    Prev
    Next
    INDEX
    Explanations

    take out loans or policies

    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
     say
    0.59
     long
    0.57
    p
    0.57
     me
    0.56
     ham
    0.55
     boy
    0.54
     rudder
    0.54
    ech
    0.54
     get
    0.53
     first
    0.53
    POSITIVE LOGITS
    و
    0.79
    між
    0.57
    욀
    0.57
    كيف
    0.56
    ᠨ
    0.55
    вер
    0.55
    وە
    0.54
    英國
    0.54
     attén
    0.53
    ꔹ
    0.53
    Activations Density 0.000%

    No Known Activations