© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 149848
    Prev
    Next
    INDEX
    Explanations

    complex emotion or reaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     inspiración
    0.95
    ੴ
    0.89
     pertanyaan
    0.88
     terrorists
    0.88
     rosé
    0.87
     setSelected
    0.85
    <unused596>
    0.85
     lymphoid
    0.85
     cellulite
    0.85
    <unused2189>
    0.84
    POSITIVE LOGITS
    review
    0.78
    He
    0.77
    nights
    0.76
    paypal
    0.76
    Hel
    0.74
    he
    0.73
    ব্ধ
    0.73
    Relationship
    0.71
    op
    0.71
    hew
    0.70
    Activations Density 0.000%

    No Known Activations