© 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-65K
    7. 51000
    Prev
    Next
    INDEX
    Explanations

    employer reputation

    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
    ：
    0.59
    当天
    0.47
    าย
    0.46
    人
    0.46
    يل
    0.46
    较大
    0.46
    贵
    0.46
    ฝ
    0.45
    اب
    0.45
    。
    0.45
    POSITIVE LOGITS
     orphans
    0.53
     conditioners
    0.50
     deterrence
    0.50
     standardization
    0.49
     imidazol
    0.48
     heridas
    0.48
     confessions
    0.48
     deuterium
    0.47
     indoctr
    0.47
     betrayal
    0.47
    Activations Density 0.008%

    No Known Activations