© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 4095
    Prev
    Next
    INDEX
    Explanations

    city, location, or context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    也
    2.02
    ें
    1.91
    ियों
    1.85
    이나
    1.81
    ให้
    1.74
     والذي
    1.74
    ("--------
    1.70
     बढ़ावा
    1.70
    া
    1.70
    아요
    1.67
    POSITIVE LOGITS
    yyyyyyyy
    2.39
    yyyy
    2.23
    ுள்ள
    2.09
    sized
    2.08
    larda
    1.98
     kolem
    1.98
    ない
    1.97
    lardan
    1.97
    י
    1.96
    wide
    1.95
    Activations Density 0.037%

    No Known Activations