© 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. 117640
    Prev
    Next
    INDEX
    Explanations

    friends, check, egg, law

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

    recently separated/divorced

    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
    за
    0.43
     минима
    0.43
     Мини
    0.42
     ترس
    0.42
     изба
    0.42
    كم
    0.42
     Godzilla
    0.42
    ぉ
    0.42
     радиа
    0.41
     ઘટા
    0.41
    POSITIVE LOGITS
     successor
    0.57
     autorisation
    0.49
     admirer
    0.48
    อำ
    0.48
     wife
    0.48
     predecessor
    0.48
    ibilité
    0.47
     হউক
    0.46
     handsome
    0.45
     esfor
    0.45
    Activations Density 0.001%

    No Known Activations