© 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. 16-GEMMASCOPE-2-RES-262K
    7. 104360
    Prev
    Next
    INDEX
    Explanations

    pickle file operations

    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_16_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
     have
    0.61
    Ò
    0.55
     patient
    0.54
     dwind
    0.54
     convenience
    0.53
     be
    0.52
    Ez
    0.51
    And
    0.50
     tilby
    0.50
    Have
    0.50
    POSITIVE LOGITS
     очки
    0.68
     Prothorax
    0.59
     auquel
    0.58
    ㄳ
    0.58
    cısı
    0.57
    쨰
    0.57
    andosi
    0.56
    젓
    0.56
    adients
    0.55
    atham
    0.55
    Activations Density 0.000%

    No Known Activations