© 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. 2034
    Prev
    Next
    INDEX
    Explanations

    programming code and attributes

    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
    孅
    0.22
     Elektrokhimiya
    0.21
     Tjiwarl
    0.21
     newApproved
    0.21
    abbanti
    0.20
     habeas
    0.20
    蓴
    0.20
    癇
    0.20
     crebre
    0.20
    皰
    0.20
    POSITIVE LOGITS
    _
    0.42
    Data
    0.35
    List
    0.33
    Of
    0.32
     =
    0.31
    Info
    0.31
    Img
    0.31
    Id
    0.31
    Handler
    0.31
    Manager
    0.30
    Activations Density 0.078%

    No Known Activations