© 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-262K
    7. 4067
    Prev
    Next
    INDEX
    Explanations

    introduces clauses or lists

    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_262k_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
    కీయ
    0.30
     fever
    0.27
    IF
    0.25
     கூ
    0.25
     "-"]
    0.25
     شهر
    0.25
    ↵
    0.25
    ﺢ
    0.25
    的过程中
    0.25
    வேன்
    0.24
    POSITIVE LOGITS
     which
    0.43
     ซึ่ง
    0.42
    ซึ่ง
    0.41
    which
    0.41
     whiche
    0.36
     ambayo
    0.33
     welche
    0.32
     जिसकी
    0.32
     जिसका
    0.32
     οποία
    0.31
    Activations Density 0.391%

    No Known Activations