© 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. 5927
    Prev
    Next
    INDEX
    Explanations

    thinking about something

    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
     equaling
    0.46
    ُوا
    0.46
    <unused2130>
    0.46
    ័
    0.44
    ENSATION
    0.44
     поможет
    0.43
    ീപ
    0.42
    ليم
    0.42
     intersecting
    0.42
    ူ
    0.42
    POSITIVE LOGITS
     feel
    0.65
     spend
    0.65
     fantas
    0.63
     cringe
    0.61
     Spend
    0.57
     wonder
    0.56
     wondered
    0.55
     find
    0.55
     Feel
    0.55
    觉得自己
    0.54
    Activations Density 0.001%

    No Known Activations