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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 98651
    Prev
    Next
    INDEX
    Explanations

    of the

    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_40_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
    試
    0.38
     رہ
    0.36
     вирі
    0.35
    йл
    0.35
     успі
    0.35
     кра
    0.34
    หย
    0.34
    湟
    0.33
    ヘア
    0.33
    勇
    0.33
    POSITIVE LOGITS
     jų
    0.44
    她们
    0.44
    ítani
    0.42
    ította
    0.42
     världen
    0.41
     principales
    0.41
    mıştı
    0.40
     najbolje
    0.40
    తున్నాయి
    0.40
    ították
    0.40
    Activations Density 0.000%

    No Known Activations