© 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. 114737
    Prev
    Next
    INDEX
    Explanations

    email addresses

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

    SELECT DISTINCT

    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
    have
    0.41
    ಾದರೂ
    0.40
    ጉ
    0.40
    Political
    0.40
    有的
    0.39
    이상
    0.39
    ก
    0.39
    Have
    0.39
    手中的
    0.38
    펀
    0.38
    POSITIVE LOGITS
     क्रिप्टोकर
    0.48
     பறி
    0.45
     っ
    0.42
     supprimer
    0.42
    နှုန်း
    0.42
     chỉ
    0.42
     obeyed
    0.42
     cambió
    0.42
     ο
    0.40
     würde
    0.40
    Activations Density 0.001%

    No Known Activations