© 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. 34-GEMMASCOPE-RES-131K
    7. 98934
    Prev
    Next
    INDEX
    Explanations

    multiplier methods

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

    This neuron responds to numeric expressions and mathematical notation.

    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
    arakhand
    -0.81
    hiel
    -0.75
    فاع
    -0.75
    diksi
    -0.74
     Шар
    -0.73
    로그램
    -0.73
    startup
    -0.71
    gye
    -0.70
    onResume
    -0.70
    endance
    -0.70
    POSITIVE LOGITS
     Lagrange
    1.74
     multipliers
    1.37
    lambda
    1.16
     multiplier
    1.15
     dual
    1.08
     λ
    1.02
    multiplier
    1.00
     lambda
    0.98
     Lagrangian
    0.98
     shadow
    0.94
    Activations Density 0.007%

    No Known Activations