© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11050
    Prev
    Next
    INDEX
    Explanations

    assignment and variable names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    🫶
    3.84
     TikTok
    3.74
    🥲
    3.70
    🥺
    3.65
    🤍
    3.65
     🥰
    3.64
     COVID
    3.62
    🥹
    3.55
    🫡
    3.45
    🥰
    3.45
    POSITIVE LOGITS
    
    2.88
     изпол
    2.05
     muß
    1.96
    牞
    1.91
    􀂃
    1.86
     handicapped
    1.80
     xrange
    1.80
    geqq
    1.78
    ;_
    1.77
     হরত
    1.74
    Activations Density 1.559%

    No Known Activations