© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 162476
    Prev
    Next
    INDEX
    Explanations

    word and subsequent word

    np_acts-logits-general · gemini-2.5-flash-lite

    supervised learning from data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     తగ్గి
    0.46
    ك
    0.44
    <0xB8>
    0.44
     biscuits
    0.43
     spans
    0.41
    ты
    0.40
    ارات
    0.39
    reiro
    0.39
     spanning
    0.39
     했을
    0.38
    POSITIVE LOGITS
    氛围
    0.49
     Selon
    0.48
    rH
    0.48
    uso
    0.45
     perpetuate
    0.45
    捅
    0.45
    andin
    0.44
     lối
    0.44
    ザ
    0.44
    クル
    0.44
    Activations Density 0.001%

    No Known Activations