© 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. 134232
    Prev
    Next
    INDEX
    Explanations

    patient, benefits, achieved

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

    code analysis calling specific API

    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
    癌
    0.47
     hôtels
    0.43
     questioned
    0.42
     creatinine
    0.42
    ⚊
    0.42
    Creative
    0.42
    ogly
    0.41
    Cafe
    0.41
    枪
    0.41
     renters
    0.40
    POSITIVE LOGITS
    erkt
    0.47
    槳
    0.46
    ื่ม
    0.45
    كاته
    0.44
     montar
    0.43
    ेलकम
    0.42
     pomocą
    0.41
     contatto
    0.41
     contacto
    0.40
    ുതി
    0.40
    Activations Density 0.000%

    No Known Activations