© 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. 39483
    Prev
    Next
    INDEX
    Explanations

    buy screen resistant

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

    while, possible, passed, sing, whether

    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
    াবেন
    0.46
     Premiership
    0.45
     organizado
    0.45
     başarılı
    0.45
     INSURANCE
    0.44
     participación
    0.43
    㿝
    0.43
     Insurance
    0.43
    岕
    0.42
     Organizational
    0.42
    POSITIVE LOGITS
    qn
    0.44
     pebb
    0.43
     formalism
    0.41
    น
    0.40
     precisely
    0.40
     materiality
    0.40
    dm
    0.40
    lv
    0.39
    cible
    0.39
    すぎる
    0.39
    Activations Density 0.008%

    No Known Activations