© 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. 22-GEMMASCOPE-RES-131K
    7. 27769
    Prev
    Next
    INDEX
    Explanations

    java code documentation headers

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

    The neuron activates strongly on numeric literals (both integers and decimals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    mizuno
    -1.10
     obwohl
    -1.07
     budaya
    -1.06
     tidur
    -1.03
    来年
    -1.02
     templo
    -0.98
    damen
    -0.97
    』『
    -0.96
     first
    -0.95
    سطس
    -0.95
    POSITIVE LOGITS
    了下来
    1.08
    $
    1.05
     and
    1.04
    never
    0.96
    pel
    0.96
    un
    0.96
     betrachten
    0.95
    仍
    0.95
    tive
    0.94
    tias
    0.94
    Activations Density 0.022%

    No Known Activations