© 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. 68050
    Prev
    Next
    INDEX
    Explanations

    reduction, financial, research, outcomes

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

    The neuron selectively activates on numeric tokens and figures (e.g. digits, percentages, counts).

    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
    textview
    -1.18
     növény
    -1.10
     trône
    -1.01
     Podemos
    -1.00
     chiffon
    -1.00
     interieur
    -1.00
     printemps
    -0.98
    autorisation
    -0.98
    CHINA
    -0.98
    polish
    -0.98
    POSITIVE LOGITS
     chose
    1.17
     post
    1.15
     financial
    1.14
     monetary
    1.14
     lifetime
    1.13
     initial
    1.09
     research
    1.09
     success
    1.09
     opciones
    1.08
     follow
    1.06
    Activations Density 0.134%

    No Known Activations