© 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. 14183
    Prev
    Next
    INDEX
    Explanations

    prefix + continuation

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

    The neuron selectively fires on extremely short tokens (one to three characters long).

    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
     in
    -3.48
     to
    -2.80
     for
    -2.66
     has
    -2.58
     Only
    -2.36
     at
    -2.31
     was
    -2.20
     be
    -2.17
     if
    -2.14
     can
    -2.13
    POSITIVE LOGITS
    鱨
    2.83
    “
    2.50
     菇
    2.25
    蟶
    2.25
     花纹
    2.17
     grec
    2.16
     工房
    2.16
     própri
    2.16
    缑
    2.09
    别人
    2.08
    Activations Density 0.000%

    No Known Activations