© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7175
    Prev
    Next
    INDEX
    Explanations

    square brackets and other 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_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
    tyard
    0.47
    thorpe
    0.47
     sensibil
    0.47
    $.;
    0.47
     landowner
    0.46
    ⚉
    0.46
     thự
    0.43
    طيب
    0.43
    หาคม
    0.43
     دکھ
    0.43
    POSITIVE LOGITS
     equations
    0.46
     brackets
    0.46
     WITH
    0.45
    写
    0.44
    amsmath
    0.44
    equation
    0.43
    with
    0.43
    equations
    0.43
     equation
    0.42
    ==============]
    0.42
    Activations Density 0.042%

    No Known Activations