© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5413
    Prev
    Next
    INDEX
    Explanations

    Savvy, trivialize, avenger, havens, savory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_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
     અસર
    0.73
    وضوع
    0.67
    াবির
    0.65
     <<
    0.65
    ribe
    0.64
    ક્ટ
    0.62
    কট
    0.62
     suje
    0.61
    ة
    0.60
     CU
    0.59
    POSITIVE LOGITS
    ्ह
    0.79
     entero
    0.69
     बढ़ना
    0.66
    تاء
    0.66
    гар
    0.65
    探し
    0.64
    呑
    0.64
     shoe
    0.61
     Domb
    0.61
     Divine
    0.61
    Activations Density 0.097%

    No Known Activations