© 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-65K
    7. 63566
    Prev
    Next
    INDEX
    Explanations

    comparison and function

    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_65k_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
    observable
    0.45
    etsu
    0.43
     observable
    0.43
     nitrification
    0.43
     encourages
    0.43
     encouraged
    0.42
    ༦
    0.41
    直径
    0.41
     Observable
    0.40
     lubrication
    0.40
    POSITIVE LOGITS
     și
    0.46
     sonrası
    0.43
    and
    0.43
     and
    0.42
     açısından
    0.42
    b
    0.42
     và
    0.41
     çı
    0.41
     öz
    0.40
    ledi
    0.39
    Activations Density 0.022%

    No Known Activations