© 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-16K
    7. 3419
    Prev
    Next
    INDEX
    Explanations

    faster data loading

    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_16k_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
    ATIVA
    0.88
    ristmas
    0.88
    ANTS
    0.88
     公
    0.86
    ánicas
    0.83
    тное
    0.83
    특별시
    0.83
    Pclass
    0.82
     वोल्ट
    0.80
    poco
    0.80
    POSITIVE LOGITS
    ться
    0.96
    стви
    0.86
    ਚ
    0.79
    вки
    0.77
    やって
    0.76
     depan
    0.76
    }],
    0.76
     glaub
    0.76
     racked
    0.75
     worded
    0.75
    Activations Density 0.001%

    No Known Activations