© 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. 4736
    Prev
    Next
    INDEX
    Explanations

    ! as a marker

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

    <!DOCTYPE

    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
    母親
    0.40
     Saturday
    0.38
    getRandom
    0.37
    嬸
    0.37
    母亲
    0.37
     အရ
    0.37
     Taunton
    0.36
    ごろ
    0.36
     stroll
    0.36
     والدہ
    0.35
    POSITIVE LOGITS
    DOCTYPE
    0.73
    doctype
    0.64
    CDATA
    0.59
    #$%
    0.48
    doc
    0.47
     warn
    0.44
     doct
    0.44
     dok
    0.43
    <!
    0.43
     Dok
    0.43
    Activations Density 0.010%

    No Known Activations