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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 117757
    Prev
    Next
    INDEX
    Explanations

    entail

    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
    ك
    0.96
    ل
    0.89
    ка
    0.88
    ب
    0.81
    ɽ
    0.77
    ャ
    0.74
    ির
    0.73
    ה
    0.71
     Rafał
    0.69
    クロマト
    0.69
    POSITIVE LOGITS
    u
    0.96
    of
    0.82
    在
    0.78
    ）
    0.75
     kein
    0.73
    to
    0.71
    ↵
    0.70
     entail
    0.70
     innebär
    0.70
    o
    0.69
    Activations Density 0.001%

    No Known Activations