© 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. 137097
    Prev
    Next
    INDEX
    Explanations

    costs, cuts, deals, flexibility, times

    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
    ಸ್ಕೊ
    0.43
     시대
    0.41
    r
    0.40
     sắc
    0.40
     fisik
    0.40
    araja
    0.39
     físicos
    0.39
    सबुक
    0.38
    isać
    0.38
    ंगाई
    0.38
    POSITIVE LOGITS
     à
    0.52
     WALTER
    0.49
     compradores
    0.46
     ಎರಡ
    0.46
    remain
    0.44
     تبقى
    0.44
     americana
    0.44
     குறைந்த
    0.43
     સરળ
    0.43
     potenciales
    0.43
    Activations Density 0.014%

    No Known Activations