© 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. 17131
    Prev
    Next
    INDEX
    Explanations

    football wide receivers

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

    football receiver

    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
    国防
    0.46
     goalie
    0.40
    oracle
    0.40
    かります
    0.38
     નિય
    0.38
    禦
    0.38
    ietic
    0.38
     oracle
    0.37
    谕
    0.37
    க்
    0.37
    POSITIVE LOGITS
     receiver
    1.28
     receivers
    1.28
     Receiver
    1.24
    receiver
    1.13
     WR
    1.11
    Receiver
    1.07
     receptor
    1.01
     receptions
    0.94
     reception
    0.93
     Receptor
    0.93
    Activations Density 0.039%

    No Known Activations