© 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. 3589
    Prev
    Next
    INDEX
    Explanations

    look forward

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

    forward

    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
    ooli
    0.40
    mouseleave
    0.38
     ካ
    0.38
     કિ
    0.35
    ິ
    0.35
     ವ್ಯಾ
    0.35
    氲
    0.35
    ⚈
    0.35
    
    0.34
    addContainerGap
    0.34
    POSITIVE LOGITS
     forward
    4.91
    forward
    4.59
     Forward
    4.53
    Forward
    4.50
     forwards
    3.97
    FORWARD
    3.88
     forwarding
    3.53
     вперед
    3.33
     forwarded
    3.27
    向前
    2.91
    Activations Density 0.193%

    No Known Activations