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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17518
    Prev
    Next
    INDEX
    Explanations

    rec with following parts of words

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

    Recurrent Neural Networks

    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
     restauration
    0.45
     acaso
    0.44
    urée
    0.42
     resumption
    0.42
    突き
    0.41
     مک
    0.40
    ოვანი
    0.40
    ق
    0.40
     diox
    0.39
     retrou
    0.39
    POSITIVE LOGITS
     Rec
    1.09
    Rec
    1.01
     rec
    0.92
    rec
    0.88
     REC
    0.83
    REC
    0.77
     reciprocity
    0.62
    iprocal
    0.61
     rek
    0.57
    收
    0.55
    Activations Density 0.036%

    No Known Activations