© 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. 163189
    Prev
    Next
    INDEX
    Explanations

    Holy Spirit

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

    U-boot or converts

    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
    Согласно
    0.49
    рами
    0.47
    '
    0.47
    焊接
    0.46
    ЗИ
    0.45
     сообщение
    0.45
    controller
    0.45
    மின்
    0.44
    ЛИ
    0.44
    Нет
    0.44
    POSITIVE LOGITS
     postures
    0.46
     chronic
    0.45
     beyond
    0.44
     apprais
    0.44
     opposites
    0.44
     impairs
    0.43
     inco
    0.42
     chronically
    0.42
     unknowingly
    0.42
     ç
    0.41
    Activations Density 0.001%

    No Known Activations