© 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
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 288
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_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
    า
    0.94
     (
    0.86
    یم
    0.84
    я
    0.76
    ல்
    0.75
    하다
    0.75
    ્સ
    0.75
     congregate
    0.74
    ки
    0.74
    ες
    0.74
    POSITIVE LOGITS
    2
    1.12
    ৬
    1.01
    У
    0.99
    ৮
    0.95
    ak
    0.92
    О
    0.91
    २
    0.89
    7
    0.88
    在
    0.85
    ৫
    0.85
    Activations Density 1.660%

    No Known Activations