© 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. 50283
    Prev
    Next
    INDEX
    Explanations

    supply from common global not red

    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
    するために
    0.42
    経営
    0.42
    靕
    0.41
    Ũ
    0.39
     বাধা
    0.39
     dictated
    0.38
     gazed
    0.38
     неравен
    0.38
    㷅
    0.38
     テーマ
    0.38
    POSITIVE LOGITS
    scott
    0.46
    otide
    0.45
    kenny
    0.44
    Lower
    0.44
    Standard
    0.42
     Hem
    0.42
    #
    0.42
    COVER
    0.41
    thern
    0.41
    CAR
    0.41
    Activations Density 0.002%

    No Known Activations