© 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. 156029
    Prev
    Next
    INDEX
    Explanations

    German literature, now online, Master training

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

    AI, resonate, having conversations

    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
     ただ
    0.60
    ностей
    0.54
    cadia
    0.52
     좋다
    0.51
     Notwithstanding
    0.50
    त्त
    0.50
    <unused382>
    0.49
     いう
    0.49
     quizá
    0.49
    <unused295>
    0.48
    POSITIVE LOGITS
    (
    0.52
     ση
    0.46
    本身的
    0.45
     offense
    0.43
     Delivery
    0.43
     offence
    0.43
    送料
    0.43
     bit
    0.42
     illegal
    0.41
    自身的
    0.40
    Activations Density 0.002%

    No Known Activations