© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1610
    Prev
    Next
    INDEX
    Explanations

    let's or here's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     "'
    3.65
     "
    3.58
    。"
    3.34
     '"
    3.33
     '
    3.21
    "'
    3.16
    '"
    3.12
     "...
    3.11
    ："
    3.03
     "[
    2.93
    POSITIVE LOGITS
    …’
    3.77
    …”
    3.66
    ”…
    3.58
    ’,
    3.33
    ’.
    3.15
    …..
    3.14
    ……”
    3.13
    !’
    3.12
     ‘
    3.09
    ’!
    3.09
    Activations Density 6.519%

    No Known Activations