© 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. 9803
    Prev
    Next
    INDEX
    Explanations

    checks in code

    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
    ประชา
    0.45
    惻
    0.42
    sière
    0.39
     hysterical
    0.39
    isées
    0.39
     அலெக்ஸாண்ட்
    0.39
    ⵣ
    0.37
    Baş
    0.37
     प्रमाणपत्र
    0.37
    اداس
    0.36
    POSITIVE LOGITS
     Diving
    0.36
    وهات
    0.36
     µ
    0.34
    )]=
    0.33
     t
    0.33
     দেখো
    0.33
     diving
    0.33
    &=
    0.33
     Bridges
    0.33
     equals
    0.32
    Activations Density 0.056%

    No Known Activations