© 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. 1548
    Prev
    Next
    INDEX
    Explanations

    sample texts

    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
    лки
    2.13
    ত্ব
    2.02
     prévention
    1.85
    ó
    1.84
     terasa
    1.84
     bientôt
    1.82
    ত্বের
    1.77
    ระดับ
    1.76
     móvil
    1.75
     barat
    1.73
    POSITIVE LOGITS
    ان
    2.44
    ्स
    2.08
    то
    2.03
    1
    1.98
    NSE
    1.84
    多い
    1.81
    
    1.80
     CONCLUSIONS
    1.76
     Subram
    1.74
    izdat
    1.74
    Activations Density 0.031%

    No Known Activations