© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30958
    Prev
    Next
    INDEX
    Explanations

    new era, my exterior, bright golden, wise power

    np_acts-logits-general · gemini-2.5-flash-lite

    negative prompts: cartoon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iz
    0.52
    ill
    0.48
    ハ
    0.48
    pang
    0.48
    ह
    0.48
    त्रा
    0.47
    usual
    0.46
    午前
    0.46
     grams
    0.45
    ธ
    0.45
    POSITIVE LOGITS
     Netzwerk
    0.50
     činjen
    0.49
     envisage
    0.49
     Швейца
    0.48
     sì
    0.45
     propriétés
    0.44
     rése
    0.44
     réseau
    0.43
     Pflege
    0.43
    鲢
    0.43
    Activations Density 0.000%

    No Known Activations