© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 8642
    Prev
    Next
    INDEX
    Explanations

    resources and people

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

    resources

    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
     Ernest
    0.43
    Ernest
    0.40
     lug
    0.38
     Lug
    0.38
    ង់
    0.37
    梅
    0.37
     Nunn
    0.36
     梅
    0.35
    দ্রোহ
    0.35
    Lug
    0.35
    POSITIVE LOGITS
     resources
    4.69
    資源
    4.69
     resource
    4.66
    资源
    4.66
     ресур
    4.41
    resource
    4.38
    resources
    4.34
    资源的
    4.31
     recursos
    4.28
     Resources
    4.25
    Activations Density 0.290%

    No Known Activations