© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11254
    Prev
    Next
    INDEX
    Explanations

    separators and delimiters

    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_40_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
     UnwrapRef
    0.41
    یی
    0.40
    ἲ
    0.40
    ناه
    0.40
     formations
    0.40
    =['
    0.39
     Vulner
    0.39
     vulner
    0.38
    峒
    0.38
    帑
    0.38
    POSITIVE LOGITS
     separator
    1.73
     separating
    1.59
     separators
    1.59
    separator
    1.53
     Separ
    1.52
     comma
    1.51
     separated
    1.48
    Separator
    1.46
     separation
    1.41
     separations
    1.41
    Activations Density 0.273%

    No Known Activations