© 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. 61564
    Prev
    Next
    INDEX
    Explanations

    instructions and actions

    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
    ᚖ
    0.55
    ٰی
    0.47
     forceful
    0.47
    NumberOperation
    0.43
     ۔
    0.43
    monotonic
    0.43
    查找
    0.42
    XYGEN
    0.42
     ק
    0.41
    FloatField
    0.41
    POSITIVE LOGITS
    蟶
    0.44
     Struktur
    0.43
    വസ
    0.41
     settembre
    0.39
    ക്കാം
    0.39
     지금
    0.38
    visi
    0.38
     diting
    0.37
     Sept
    0.37
    elä
    0.37
    Activations Density 0.002%

    No Known Activations