© 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-16K
    7. 7929
    Prev
    Next
    INDEX
    Explanations

    let binding and initialization

    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_16k_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
     receptor
    0.45
     受
    0.43
     wafers
    0.43
     駅
    0.42
     astring
    0.41
     HOSP
    0.40
     dysfunctional
    0.40
     ▶
    0.40
     abscess
    0.39
     usurp
    0.39
    POSITIVE LOGITS
    ioso
    0.41
     விச
    0.41
    Benjamin
    0.39
     Kuhn
    0.38
    솜
    0.38
     Benjamin
    0.38
    benar
    0.38
    ío
    0.38
    녕
    0.37
    issage
    0.37
    Activations Density 0.013%

    No Known Activations