© 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. 1996
    Prev
    Next
    INDEX
    Explanations

    listing items and 'Quitting'

    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
    tener
    2.23
    𝐚
    2.18
    an
    2.15
    ição
    2.13
    antha
    2.11
    𝐨
    2.09
    ten
    2.09
    spect
    2.07
    ्ता
    2.02
    o
    2.01
    POSITIVE LOGITS
     crc
    2.18
     ['$
    2.07
    webtoken
    2.01
     !_
    1.98
    زاد
    1.89
    ProductRunnable
    1.89
    цо
    1.79
     neder
    1.77
    OrEqualTo
    1.77
    یاز
    1.74
    Activations Density 0.261%

    No Known Activations