© 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. 30303
    Prev
    Next
    INDEX
    Explanations

    set of X

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

    The neuron fires on numeric tokens—particularly integer counts or measurements—embedded 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_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
    鼋
    -1.37
     périodes
    -1.34
    <bos>
    -1.31
     gamut
    -1.31
     legions
    -1.26
    ELTS
    -1.23
     extent
    -1.23
     list
    -1.22
    hoppers
    -1.22
    ogues
    -1.20
    POSITIVE LOGITS
     mostly
    1.70
     about
    1.57
     five
    1.50
     very
    1.45
     fairly
    1.44
     what
    1.43
     highly
    1.41
     eight
    1.41
     seven
    1.39
     similar
    1.36
    Activations Density 0.158%

    No Known Activations