© 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. 40820
    Prev
    Next
    INDEX
    Explanations

    pwd command

    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
    '
    1.26
    ess
    1.16
    is
    1.06
    em
    1.01
    ين
    0.93
    larni
    0.91
    elle
    0.89
    ához
    0.89
     archivos
    0.88
    ونها
    0.88
    POSITIVE LOGITS
    ו
    1.06
    ้า
    0.92
     mezzanine
    0.90
    O
    0.87
     katva
    0.86
     margarine
    0.85
     เพื่อ
    0.84
    з
    0.84
     ซึ่ง
    0.84
     hesitation
    0.84
    Activations Density 0.001%

    No Known Activations