© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7229
    Prev
    Next
    INDEX
    Explanations

    Arts and Canvas Events

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

    catch and caught

    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
    ित
    0.50
    itanie
    0.44
     আশীর
    0.40
    Yves
    0.39
     Sera
    0.39
    仃
    0.38
     translateX
    0.38
    ydd
    0.38
    ="">
    0.37
    كيف
    0.37
    POSITIVE LOGITS
    abouts
    0.44
    Caught
    0.42
    caught
    0.40
     Caught
    0.40
    Peg
    0.39
     startled
    0.39
     multib
    0.39
     catching
    0.38
    Glass
    0.38
    帽
    0.38
    Activations Density 0.000%

    No Known Activations