© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12712
    Prev
    Next
    INDEX
    Explanations

    stoic, vintage, Pro

    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
    s
    1.85
     povas
    1.77
    tion
    1.66
    yang
    1.64
    tien
    1.64
    র
    1.61
    tin
    1.61
     ->
    1.61
    sels
    1.60
    が
    1.59
    POSITIVE LOGITS
     chiếm
    2.07
    cedented
    1.95
     intense
    1.89
     yoğun
    1.83
    ඨ
    1.79
    𝑒
    1.79
    ඥ
    1.76
     sắp
    1.75
     buồn
    1.74
     ausencia
    1.72
    Activations Density 21.291%

    No Known Activations