© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 10170
    Prev
    Next
    INDEX
    Explanations

    hot followed by topic, wife, girl, cocoa

    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_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
    瘩
    1.96
     daí
    1.92
    쪽
    1.92
    тивным
    1.91
     cometido
    1.90
    ী
    1.90
     erau
    1.88
    んですよね
    1.87
     cuyo
    1.85
     térmica
    1.85
    POSITIVE LOGITS
    نا
    1.97
    ש
    1.91
    но
    1.70
    lardır
    1.66
    ш
    1.59
    ان
    1.55
    тан
    1.52
    lardan
    1.49
    на
    1.48
    lah
    1.47
    Activations Density 0.097%

    No Known Activations