© 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. 190078
    Prev
    Next
    INDEX
    Explanations

    Nicki Minaj

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

    Procter & Gamble, Trinidad, Harris, notice

    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
     pene
    0.40
    ູ່
    0.39
    chauff
    0.39
    👠
    0.39
    
    0.38
    genera
    0.38
     lhe
    0.38
    ™.
    0.37
    while
    0.37
    塞尔
    0.37
    POSITIVE LOGITS
    କ
    0.46
     Shukla
    0.46
     Kontext
    0.45
     Apple
    0.45
     Gaw
    0.45
     საჭ
    0.44
     상황
    0.43
    कतों
    0.42
    <0xA0>
    0.42
    Climate
    0.42
    Activations Density 0.000%

    No Known Activations