© 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-262K
    7. 120262
    Prev
    Next
    INDEX
    Explanations

    emphasizing 'so'

    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
    ר
    1.15
    t
    0.97
    는
    0.94
    다
    0.92
    ます
    0.91
    ני
    0.90
    は
    0.88
    이
    0.88
    י
    0.86
    т
    0.83
    POSITIVE LOGITS
    ু
    0.95
    ade
    0.92
    3
    0.89
    𝟑
    0.86
    é
    0.79
     času
    0.78
     bekannten
    0.75
    .³
    0.74
     ważne
    0.73
     anderen
    0.71
    Activations Density 0.001%

    No Known Activations