© 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. 27547
    Prev
    Next
    INDEX
    Explanations

    code references and specific terms

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

    This neuron activates on standalone numeric tokens (e.g. version numbers, measurements, IDs).

    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
    S
    -1.28
     principals
    -1.13
    2
    -1.07
     ‘
    -1.05
    そして
    -1.02
     ‚
    -1.01
    ]+$
    -0.99
     Everyone
    -0.97
     +
    -0.97
    F
    -0.96
    POSITIVE LOGITS
     exemplaire
    1.27
    ținut
    1.27
     quí
    1.26
     tkan
    1.25
     אָ
    1.25
     membayar
    1.25
     variés
    1.24
    nehm
    1.21
     huesos
    1.20
     rivales
    1.20
    Activations Density 0.000%

    No Known Activations