© 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. 7541
    Prev
    Next
    INDEX
    Explanations

    @Param, @Runtime, @subtype

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

    testing and composing code

    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
    私
    0.91
    Private
    0.87
    PRIVATE
    0.85
     Private
    0.84
    private
    0.79
     PRIVATE
    0.78
     प्राइवेट
    0.78
     私
    0.77
    私人
    0.77
    STATIC
    0.75
    POSITIVE LOGITS
     fingertips
    0.38
     async
    0.37
    (!)
    0.37
     jq
    0.37
    ('.')
    0.37
     decorator
    0.36
     inline
    0.36
     conservar
    0.36
    ('/')
    0.36
     decorar
    0.36
    Activations Density 0.000%

    No Known Activations