© 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. 64459
    Prev
    Next
    INDEX
    Explanations

    vs or versus

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

    The neuron fires strongly on standalone numeric tokens (e.g. scores, statistics, multi‐digit numbers).

    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
     both
    -1.12
     many
    -1.11
     in
    -1.03
     even
    -1.02
     there
    -1.02
     since
    -1.01
     an
    -1.00
     what
    -0.98
     all
    -0.98
     only
    -0.98
    POSITIVE LOGITS
     vs
    1.52
     versus
    1.36
     Versus
    1.26
    versus
    1.19
     Vs
    1.17
     XXXX
    1.15
     verses
    1.07
    vs
    0.98
     DIFFERENT
    0.96
    黠
    0.95
    Activations Density 0.007%

    No Known Activations