© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14586
    Prev
    Next
    INDEX
    Explanations

    feeling watched or weighted

    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_7_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
    ness
    2.12
    ly
    1.85
    s
    1.84
    r
    1.76
    t
    1.75
    다고
    1.71
    temporary
    1.69
    surface
    1.68
    nin
    1.63
    了
    1.60
    POSITIVE LOGITS
     sguardo
    1.99
    šli
    1.94
     güncelle
    1.84
     domanda
    1.81
     richiesta
    1.80
     veröffentlicht
    1.78
    operand
    1.76
    ڻ
    1.76
    ﺙ
    1.76
     schafft
    1.76
    Activations Density 0.192%

    No Known Activations