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

    Neuronpedia

    Jacobian LensNEW
    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. 36468
    Prev
    Next
    INDEX
    Explanations

    specific grammatical structures

    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
     Younger
    0.91
    ढ़
    0.86
     ★★
    0.83
     bk
    0.83
     Overwatch
    0.82
     Lazada
    0.81
     levens
    0.79
     HBase
    0.78
     Meter
    0.78
     agam
    0.78
    POSITIVE LOGITS
    ご理解
    0.85
     contenuto
    0.84
    र्क
    0.83
    ع
    0.81
     fattori
    0.80
    ून
    0.78
    ensioni
    0.77
     portato
    0.76
    ко
    0.75
    ول
    0.75
    Activations Density 0.000%

    No Known Activations