© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 146537
    Prev
    Next
    INDEX
    Explanations

    forwarding business domain names

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

    list initiators

    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
     الض
    0.41
     szczeg
    0.40
     floor
    0.40
     hielo
    0.40
     problemas
    0.39
     habitación
    0.39
    "
    0.38
     排
    0.38
     K
    0.37
    ché
    0.37
    POSITIVE LOGITS
     यूनाइटेड
    0.52
    regator
    0.51
    也会
    0.48
     グッチ
    0.48
    硋
    0.48
     그다음에
    0.47
    也會
    0.47
    obedience
    0.47
     क्रमवारीत
    0.47
     इन्वेस्टमेंट
    0.47
    Activations Density 0.001%

    No Known Activations