© 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. 13394
    Prev
    Next
    INDEX
    Explanations

    loss function

    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
    轫
    2.96
    teki
    2.71
    瑭
    2.67
    ╹
    2.66
    tena
    2.63
    foil
    2.62
     personalise
    2.61
    Ꮴ
    2.61
    rivi
    2.61
    ᇁ
    2.60
    POSITIVE LOGITS
    sst
    2.41
    ין
    2.32
    sung
    2.08
     ming
    2.03
    י
    2.01
    dw
    1.90
    SnackBar
    1.89
    عرض
    1.81
    eless
    1.79
    ’
    1.78
    Activations Density 0.022%

    No Known Activations