© 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. 52452
    Prev
    Next
    INDEX
    Explanations

    generation, child, violence, calendar, compress

    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
     cars
    0.48
     znacz
    0.47
     większość
    0.45
    most
    0.44
    ;
    0.44
     jing
    0.44
     fırs
    0.44
     whale
    0.43
     ወይም
    0.43
     murders
    0.43
    POSITIVE LOGITS
    㭚
    0.55
    َي
    0.50
     Locally
    0.48
    ುಂಬ
    0.47
     Solve
    0.47
    建議
    0.47
     Locals
    0.45
     Unfortunately
    0.45
    ુ
    0.45
    閭
    0.44
    Activations Density 0.001%

    No Known Activations