© 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. 31-GEMMASCOPE-2-RES-262K
    7. 101060
    Prev
    Next
    INDEX
    Explanations

    Canal Charm Development District Cruise

    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_31_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
     equilibrated
    0.46
    ’
    0.44
     DAG
    0.42
    ilerine
    0.42
    穩定
    0.42
    iga
    0.42
    )
    0.41
     возник
    0.41
    不安定
    0.40
     Received
    0.39
    POSITIVE LOGITS
    ጲ
    0.54
     résident
    0.50
     inté
    0.46
    печа
    0.46
     všet
    0.45
     lineman
    0.45
     escort
    0.44
    Underwater
    0.44
     straighten
    0.43
     刘
    0.43
    Activations Density 0.003%

    No Known Activations