© 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. 41-GEMMASCOPE-2-RES-262K
    7. 2874
    Prev
    Next
    INDEX
    Explanations

    parti status

    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_all/layer_41_width_262k_l0_big
    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
    तुरंग
    0.59
    ាតុ
    0.52
     Danish
    0.50
    ㄆ
    0.49
     rechte
    0.47
     intercourse
    0.47
    Sweden
    0.47
    Denmark
    0.46
     mädchen
    0.46
     behavioral
    0.46
    POSITIVE LOGITS
     som
    0.59
     både
    0.53
     en
    0.51
    Det
    0.51
     på
    0.49
    는
    0.48
    나
    0.48
     till
    0.48
     naturl
    0.46
    ologisk
    0.46
    Activations Density 0.001%

    No Known Activations