© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2244
    Prev
    Next
    INDEX
    Explanations

    no obligation

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

    hacker Culture, AnyLogic, plate, Triennial, assessments

    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_53_width_65k_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
     ಬಳ
    0.42
     স্থাপ
    0.40
     polož
    0.39
    ્યાર
    0.39
     দ্ব
    0.38
     thuộc
    0.38
    剂
    0.38
    icking
    0.37
     পেয়েছে
    0.37
     होऊन
    0.37
    POSITIVE LOGITS
     relation
    0.44
     IO
    0.43
     pleasure
    0.41
     مك
    0.39
    <0xA0>
    0.39
     रिलेशन
    0.38
     marvel
    0.38
    रत
    0.38
     大人
    0.38
     Adult
    0.37
    Activations Density 0.000%

    No Known Activations