© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 333
    Prev
    Next
    INDEX
    Explanations

    Lawrence MacAulay

    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
    Bibliography
    0.78
     развитии
    0.77
    льных
    0.74
    ியம்
    0.74
     результате
    0.73
     metais
    0.71
    IPAL
    0.71
    ش
    0.71
    苾
    0.70
     развитию
    0.68
    POSITIVE LOGITS
    Д
    0.86
    F
    0.80
     peptides
    0.79
    Мо
    0.77
    𝙎
    0.77
    Μ
    0.77
     dieta
    0.76
     savoir
    0.75
    )，
    0.74
    ד
    0.74
    Activations Density 0.000%

    No Known Activations