© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 5901
    Prev
    Next
    INDEX
    Explanations

    club

    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
    क
    1.96
    ح
    1.86
    ية
    1.48
    ק
    1.47
    я
    1.45
    iz
    1.38
    ل
    1.38
    ร
    1.37
    č
    1.36
    راً
    1.34
    POSITIVE LOGITS
    ように
    1.98
    𝖽
    1.76
    𝗌
    1.75
     وعلى
    1.73
    𝘱
    1.68
     edilen
    1.63
    mitglied
    1.61
     dimers
    1.58
     adicion
    1.57
     andando
    1.57
    Activations Density 0.003%

    No Known Activations