© 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. 6784
    Prev
    Next
    INDEX
    Explanations

    ending words

    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
    з
    1.66
    朶
    1.34
    theorem
    1.31
    usiasm
    1.31
    Cart
    1.29
    spacing
    1.28
     وحتى
    1.28
    revenue
    1.26
    structure
    1.25
    smallest
    1.25
    POSITIVE LOGITS
    ку
    1.48
    <0x11>
    1.38
    ור
    1.26
     crimin
    1.20
    ेट्टी
    1.15
     crucified
    1.14
    }},
    1.13
    iation
    1.13
    
    1.13
     χώρα
    1.12
    Activations Density 0.000%

    No Known Activations