© 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. 34-GEMMASCOPE-RES-131K
    7. 47822
    Prev
    Next
    INDEX
    Explanations

    based on

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

    This neuron activates on numeric figures and measurements (e.g., counts, statistics, coordinates, percentages).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    paux
    -0.98
     and
    -0.96
    elesai
    -0.94
    immen
    -0.91
     []:
    -0.90
     {
    -0.89
     MessageBoxIcon
    -0.87
    Filmography
    -0.87
     piscinas
    -0.87
     it
    -0.84
    POSITIVE LOGITS
     based
    2.31
     from
    1.55
    based
    1.38
     meant
    1.20
     obtained
    1.19
     derived
    1.18
     taken
    1.17
    あくまで
    1.17
    BASED
    1.15
    あく
    1.10
    Activations Density 0.067%

    No Known Activations