© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69680
    Prev
    Next
    INDEX
    Explanations

    +/- numbers

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

    The neuron fires on numerical measurement values (especially decimals and statistics) in the text.

    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
     what
    -2.30
     a
    -2.03
     one
    -1.99
     an
    -1.93
     it
    -1.71
     just
    -1.66
     only
    -1.66
     from
    -1.60
    :
    -1.53
     if
    -1.52
    POSITIVE LOGITS
     många
    1.72
     этого
    1.52
    甚至
    1.52
     trámites
    1.48
    因为
    1.48
    ("")]
    1.44
     mismos
    1.40
    NgModule
    1.39
     alrededores
    1.39
     вас
    1.38
    Activations Density 0.143%

    No Known Activations