© 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-262K
    7. 4153
    Prev
    Next
    INDEX
    Explanations

    SQL query keywords

    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
     ateş
    0.46
    لمات
    0.41
    äß
    0.40
    Chromatic
    0.39
    糁
    0.39
     Schrö
    0.39
     வேண்டு
    0.39
     lézards
    0.38
     Slav
    0.38
     Worte
    0.38
    POSITIVE LOGITS
    且
    0.51
     AND
    0.49
     ORDER
    0.45
     >
    0.45
     !=
    0.44
    query
    0.44
     LIKE
    0.43
     または
    0.43
    查询
    0.43
    ={
    0.42
    Activations Density 0.102%

    No Known Activations