© 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. 40-GEMMASCOPE-2-RES-262K
    7. 133676
    Prev
    Next
    INDEX
    Explanations

    mac adres to macadres

    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_40_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
    ហេ
    0.49
    ্া
    0.43
     hesitation
    0.41
    ភាព
    0.40
     InputAction
    0.39
    ඩ්
    0.39
    껄
    0.39
    Становништво
    0.38
    জম
    0.38
    𝘬
    0.38
    POSITIVE LOGITS
    8
    0.40
    تق
    0.39
    Spot
    0.39
     Workplace
    0.37
    Ві
    0.37
     ,
    0.36
    ارف
    0.36
    献
    0.36
     Aktiv
    0.35
    Welcome
    0.34
    Activations Density 0.000%

    No Known Activations