© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47789
    Prev
    Next
    INDEX
    Explanations

    stunning

    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
    Нау
    0.57
    алы
    0.52
    نان
    0.50
    Dental
    0.47
    ⵕ
    0.46
    لا
    0.45
    messages
    0.45
    இந்திய
    0.45
    Аль
    0.45
    ⵍ
    0.44
    POSITIVE LOGITS
     Chengdu
    0.56
     nasty
    0.54
     put
    0.52
     mentor
    0.52
     st
    0.50
     at
    0.49
     conco
    0.49
     start
    0.48
     room
    0.48
     parmesan
    0.48
    Activations Density 0.002%

    No Known Activations