© 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. 114676
    Prev
    Next
    INDEX
    Explanations

    King Paul II

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

    specific words and their follow-ups

    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
    downs
    0.46
     instantaneously
    0.44
    mac
    0.43
    侃
    0.43
    チャー
    0.43
     الحكوم
    0.42
    tickers
    0.40
     Throat
    0.40
    ión
    0.40
    мулятор
    0.40
    POSITIVE LOGITS
     proj
    0.47
     pdelay
    0.47
     diad
    0.46
    ستی
    0.46
     penit
    0.46
    Analytical
    0.46
     stupe
    0.46
     fint
    0.46
    孽
    0.46
     kredi
    0.46
    Activations Density 0.000%

    No Known Activations