© 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. 43191
    Prev
    Next
    INDEX
    Explanations

    module license declarations

    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
     s
    0.92
     l
    0.91
     Your
    0.88
     L
    0.84
    ्स
    0.84
     P
    0.82
    s
    0.82
    を引き
    0.81
     חד
    0.80
     인천
    0.77
    POSITIVE LOGITS
    лку
    1.05
    が多く
    1.03
    plicates
    1.02
    かった
    1.02
    と思います
    1.00
    ጩ
    0.98
    mtrl
    0.98
    tional
    0.96
    脩
    0.96
    fighters
    0.96
    Activations Density 0.000%

    No Known Activations