© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5673
    Prev
    Next
    INDEX
    Explanations

    RJ, Buj, Moj, FJ, aji, raj, ji, conj

    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_31_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
     variegated
    0.58
    perti
    0.57
    uose
    0.56
    oq
    0.56
     நாடு
    0.56
    }",
    0.55
    />}
    0.53
     antisense
    0.51
     minh
    0.51
    नम
    0.50
    POSITIVE LOGITS
    unctive
    0.83
    ्ज
    0.83
    ्ञ
    0.77
    ્ઞ
    0.67
    ող
    0.65
    ｬ
    0.64
    unct
    0.63
    ेट
    0.62
    avascript
    0.62
    AX
    0.61
    Activations Density 0.187%

    No Known Activations