© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7117
    Prev
    Next
    INDEX
    Explanations

    felony, felon, felt, Felix

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

    felix, felis, felidae, felony, falafel

    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
    薊
    0.41
     Phantom
    0.40
     দুধ
    0.38
    菰
    0.38
     phantom
    0.37
     Crop
    0.36
    宙
    0.36
    敂
    0.36
    寐
    0.35
    wnie
    0.35
    POSITIVE LOGITS
     fel
    4.03
    Fel
    3.94
     Fel
    3.91
     FEL
    3.83
    fel
    3.80
    FEL
    3.70
    Felix
    3.42
     Felix
    3.38
     Félix
    2.92
     Felt
    2.89
    Activations Density 0.055%

    No Known Activations