© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13662
    Prev
    Next
    INDEX
    Explanations

    analog

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_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
    .'</
    0.75
    𒐪
    0.73
     digitalisation
    0.71
    শংস
    0.70
    向けの
    0.70
    ੍
    0.69
     '[
    0.69
    ",'
    0.68
    ᵉ
    0.68
     authorisation
    0.67
    POSITIVE LOGITS
    
    1.23
     
    1.20
    
    1.19
     “…
    1.12
    
    1.11
     
    1.10
    
    1.10
     BUT
    1.09
    
    1.09
    
    1.09
    Activations Density 0.005%

    No Known Activations