© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 93501
    Prev
    Next
    INDEX
    Explanations

    occupation, location, or descriptive keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     구조
    0.54
     ۲
    0.48
    峻
    0.48
     erhö
    0.48
    ಾಗಿತ್ತು
    0.47
    اریخ
    0.47
     प्रश्
    0.46
    <unused393>
    0.46
     भाजप
    0.46
     രണ്ട
    0.46
    POSITIVE LOGITS
    -
    0.51
    .
    0.50
     Lat
    0.44
    5
    0.43
    Whis
    0.42
     lat
    0.41
     Wesleyan
    0.41
    Bat
    0.41
    isn
    0.40
    1
    0.40
    Activations Density 0.000%

    No Known Activations