© 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. 3530
    Prev
    Next
    INDEX
    Explanations

    capital of australia

    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
    ्स
    1.96
    ない
    1.70
    맙
    1.70
    да
    1.60
    skraft
    1.57
    gewicht
    1.56
    س
    1.56
    тэй
    1.55
    gia
    1.53
    gruppen
    1.53
    POSITIVE LOGITS
    जो
    1.66
    ளில்
    1.62
    한
    1.52
    вой
    1.51
    ட
    1.49
    во
    1.48
    ной
    1.47
    처럼
    1.45
    ل
    1.45
    about
    1.44
    Activations Density 0.001%

    No Known Activations