© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 169979
    Prev
    Next
    INDEX
    Explanations

    Japanese immigrants

    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
    ᓛ
    0.55
    ्यादा
    0.49
     मामले
    0.49
    ომ
    0.48
     হক
    0.47
    ంబేద్కర్
    0.46
     gráfica
    0.46
    颢
    0.46
     каждой
    0.45
    льные
    0.45
    POSITIVE LOGITS
     شب
    0.48
     store
    0.46
    ari
    0.46
     Samuel
    0.46
    fo
    0.46
    ritz
    0.45
    rami
    0.44
     Charlie
    0.44
     statement
    0.44
    store
    0.44
    Activations Density 0.000%

    No Known Activations