© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95632
    Prev
    Next
    INDEX
    Explanations

    musical ensembles and works

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

    The neuron is selectively activating on numeric tokens (i.e. numbers and decimal values).

    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
    new
    -1.35
     you
    -1.28
     new
    -1.23
     when
    -1.20
     jobs
    -1.19
     {
    -1.19
     *
    -1.17
    ="$(
    -1.16
     estimates
    -1.16
     time
    -1.15
    POSITIVE LOGITS
    ㄜ
    1.27
    Ficha
    1.10
    𝐽
    1.10
     автомобиль
    1.10
     pantalón
    1.09
     chré
    1.09
    Réalisation
    1.08
    pasti
    1.08
     voorbere
    1.06
     with
    1.05
    Activations Density 0.010%

    No Known Activations