© 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. 233826
    Prev
    Next
    INDEX
    Explanations

    Jewish and gentile communities

    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
     صبر
    0.51
    lees
    0.50
    辍
    0.49
    immunity
    0.47
    isShow
    0.46
    を加
    0.45
     устойчи
    0.45
    डब्ल्यू
    0.45
     patiently
    0.44
    мести
    0.44
    POSITIVE LOGITS
    otra
    0.50
    蘄
    0.43
    ación
    0.43
    ​​
    0.42
     RFID
    0.40
    ando
    0.40
    ,
    0.40
     detik
    0.40
    のお
    0.40
    azia
    0.40
    Activations Density 0.001%

    No Known Activations