© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 165808
    Prev
    Next
    INDEX
    Explanations

    deduct expenses, aesthetics

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

    explaining the why or a feature

    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_31_width_262k_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
     జ
    0.50
    emptyDict
    0.50
     자동으로
    0.50
     נישט
    0.50
    
    0.49
    ("|"+"
    0.48
    冦
    0.48
     자동
    0.48
     प्रत्ये
    0.48
    传承
    0.47
    POSITIVE LOGITS
     perché
    0.51
     decorative
    0.49
     carpets
    0.45
     as
    0.45
     acoustics
    0.45
     forehead
    0.44
     penetrating
    0.44
     acer
    0.44
     aesthetics
    0.44
    0.44
    Activations Density 0.003%

    No Known Activations