Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 3960
    Prev
    Next
    INDEX
    Explanations

    `"` around text

    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
    ا
    1.46
    ي
    1.18
    y
    1.16
    יים
    1.12
    en
    1.05
    یہ
    1.04
    ein
    1.02
    eer
    1.02
    و
    1.01
    ла
    0.99
    POSITIVE LOGITS
     positively
    0.78
    ร์
    0.72
    </strong>
    0.70
     fleste
    0.69
    
    0.69
    ্যায়
    0.67
     וכ
    0.65
    ​
    0.65
    琶
    0.65
     plight
    0.65
    Activations Density 0.425%

    No Known Activations