© 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. 5000
    Prev
    Next
    INDEX
    Explanations

    form and component relationships

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

    angular component names

    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
    _"
    0.43
    Caucasian
    0.43
     "_"
    0.38
    mRNA
    0.37
    ContextProvider
    0.37
     tracts
    0.36
    Again
    0.36
     mut
    0.36
     "__
    0.35
    Clay
    0.35
    POSITIVE LOGITS
     HomeComponent
    1.27
     AppComponent
    1.24
     LoginComponent
    1.18
    ListComponent
    1.08
    PageComponent
    1.07
    FormComponent
    1.04
    AppComponent
    1.02
     componente
    1.02
     NgModule
    1.01
    RoutingModule
    0.98
    Activations Density 0.002%

    No Known Activations