© 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. 2065
    Prev
    Next
    INDEX
    Explanations

    comes after so

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

    ligma joke

    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
    রাং
    0.41
    ﺢ
    0.40
     composants
    0.40
     मे
    0.39
     пол
    0.39
     কেনার
    0.38
     ,[
    0.38
     компонентов
    0.38
    textAllCaps
    0.38
    ☏
    0.38
    POSITIVE LOGITS
     wit
    0.42
    valu
    0.41
    समा
    0.40
     daw
    0.39
    Madison
    0.38
     witty
    0.38
     Wad
    0.38
     Madison
    0.38
     Wit
    0.37
    isbury
    0.37
    Activations Density 0.000%

    No Known Activations