© 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. 8373
    Prev
    Next
    INDEX
    Explanations

    similarity and likeness

    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
    )،
    0.57
    ास
    0.53
     Besar
    0.53
    ی
    0.51
    া
    0.50
    ل
    0.49
    ה
    0.48
    쩝
    0.47
    eseorang
    0.47
     Biết
    0.47
    POSITIVE LOGITS
    ्स
    0.61
     razie
    0.57
    ان
    0.55
    at
    0.54
    𝗮
    0.52
    ahin
    0.51
     계속
    0.51
     ней
    0.50
     hason
    0.50
    anzi
    0.50
    Activations Density 0.623%

    No Known Activations