© 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. 152057
    Prev
    Next
    INDEX
    Explanations

    formal titles followed by period

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

    dr. and ms. titles

    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
     manière
    0.49
    мережа
    0.44
     chocolates
    0.42
     maneiras
    0.42
     clever
    0.41
     t
    0.41
    ريكا
    0.40
     maneira
    0.39
    CHANNEL
    0.38
     cluttered
    0.38
    POSITIVE LOGITS
     kết
    0.49
     असेल
    0.49
     결
    0.48
     हेतु
    0.47
     נוס
    0.47
     будет
    0.47
    จะมี
    0.47
    鉭
    0.47
     جهت
    0.47
     avrà
    0.46
    Activations Density 0.009%

    No Known Activations