© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11536
    Prev
    Next
    INDEX
    Explanations

    only, just, limited

    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_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
     অবশ্যই
    0.54
     ovarian
    0.51
    多样
    0.49
     seamlessly
    0.49
     любом
    0.49
    alakip
    0.48
    𝑭
    0.48
    Об
    0.47
    WT
    0.47
     all
    0.47
    POSITIVE LOGITS
     лишь
    0.81
     মাত্র
    0.63
     wenige
    0.60
     толькі
    0.59
    แค่
    0.59
     فقط
    0.56
    只有
    0.55
     Only
    0.55
    短短
    0.55
     barely
    0.52
    Activations Density 0.071%

    No Known Activations