© 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. 14852
    Prev
    Next
    INDEX
    Explanations

    diverse scripts or characters, especially non-Latin

    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
     меся
    0.74
     attainment
    0.73
     dolayı
    0.73
    ৩
    0.71
     infliction
    0.71
     bebas
    0.70
     monotonicity
    0.68
     demikian
    0.67
     severance
    0.67
    bė
    0.67
    POSITIVE LOGITS
    ك
    1.00
    ă
    0.86
    lyPlugin
    0.84
    ल
    0.83
    к
    0.79
     UBND
    0.77
    ני
    0.74
    та
    0.73
     Після
    0.72
    ව
    0.72
    Activations Density 0.000%

    No Known Activations