© 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. 6774
    Prev
    Next
    INDEX
    Explanations

    H followed by SS, ath, edge, CL, or atoms

    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
    ш
    2.27
     Sulfur
    2.05
     Jednak
    2.03
    s
    2.00
     hype
    1.95
    रिया
    1.94
    ੋ
    1.92
     analyze
    1.90
    س
    1.87
    ಲ
    1.87
    POSITIVE LOGITS
     sido
    2.17
    ्वेस्ट
    2.17
     podido
    2.05
     pylori
    1.99
    ᱸ
    1.91
     말고
    1.85
    ércoles
    1.84
    ྥ
    1.84
    მწიფ
    1.80
    ઠળ
    1.77
    Activations Density 0.791%

    No Known Activations