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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3809
    Prev
    Next
    INDEX
    Explanations

    fans or supporters

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

    fans and admirers

    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
    庠
    0.38
     मोल
    0.37
    fluor
    0.36
    নীতিক
    0.35
    公务
    0.35
     হেতু
    0.35
     hydrol
    0.34
    被告
    0.34
     उमेदवार
    0.34
    Operators
    0.33
    POSITIVE LOGITS
     fans
    4.75
     Fans
    4.31
     fan
    4.28
    fans
    4.25
    Fans
    4.19
     팬
    4.06
    粉丝
    3.98
    ファン
    3.80
    팬
    3.72
     fãs
    3.70
    Activations Density 0.262%

    No Known Activations