© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5567
    Prev
    Next
    INDEX
    Explanations

    summary descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-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
     পিছিয়ে
    0.59
     said
    0.59
    ઢી
    0.57
    ራዊ
    0.54
    跡
    0.54
    isional
    0.53
     backside
    0.53
    ここまで
    0.53
    后
    0.53
     असल्या
    0.52
    POSITIVE LOGITS
    caya
    0.57
    ="">
    0.55
    მე
    0.54
     ዋ
    0.54
     inappropriately
    0.53
     epitopes
    0.52
    }°
    0.52
    DAQ
    0.51
     they
    0.50
    เขา
    0.50
    Activations Density 0.001%

    No Known Activations