© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99377
    Prev
    Next
    INDEX
    Explanations

    predicting "Pre" followed by word

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron doesn’t respond to any tokens—that is, it never activates and so isn’t detecting any pattern.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :
    -2.67
    s
    -2.67
    一些
    -2.53
    檮
    -2.41
    /
    -2.38
    end
    -2.34
    A
    -2.23
     is
    -2.17
     pertenec
    -2.09
     ένας
    -2.09
    POSITIVE LOGITS
    啬
    3.05
    鹇
    2.50
    ၟ
    2.36
    ,“
    2.31
    鉦
    2.30
    가
    2.27
     mohl
    2.25
    \}$.
    2.25
    𝙠
    2.25
     estímulo
    2.19
    Activations Density 0.007%

    No Known Activations