© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 7098
    Prev
    Next
    INDEX
    Explanations

    villa or villas

    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
    بة
    1.92
    يت
    1.88
    𝑆
    1.80
    بی
    1.75
    بت
    1.67
    vp
    1.66
     Soldaten
    1.66
    فی
    1.66
    ствии
    1.64
     rumors
    1.63
    POSITIVE LOGITS
    ن
    2.64
    larda
    2.42
    lás
    2.30
    l
    2.22
    न
    2.22
    erweise
    2.13
     Reim
    2.03
     cuesta
    1.95
     marred
    1.95
     chiamata
    1.95
    Activations Density 0.007%

    No Known Activations