© 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. 7325
    Prev
    Next
    INDEX
    Explanations

    copyright and copyrighted content

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

    copyright and intellectual property

    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
    _{*
    0.40
    baden
    0.38
    dbjc
    0.38
     собе
    0.37
     intercal
    0.37
     꾸
    0.37
    㳖
    0.36
     alcal
    0.36
     reconstru
    0.36
     billet
    0.36
    POSITIVE LOGITS
     copyright
    4.25
     Copyright
    4.03
    Copyright
    3.84
    copyright
    3.83
     copyrights
    3.75
     copyrighted
    3.48
     COPYRIGHT
    3.31
    版权
    3.14
     ©
    2.84
    ©
    2.58
    Activations Density 0.278%

    No Known Activations