© 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. 131028
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens, i.e. numbers appearing in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    proper nouns or specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     they
    -1.28
     them
    -1.25
    ها
    -1.16
    她
    -1.14
    これを
    -1.13
    他
    -1.09
     Donegal
    -1.04
    ile
    -1.04
    ((*
    -1.02
    </i>
    -1.00
    POSITIVE LOGITS
     the
    1.15
     mirip
    1.11
     kenapa
    1.10
     nici
    1.06
    fazer
    1.04
    Neither
    1.02
     étr
    1.02
    衙
    1.02
     mewah
    1.02
     neither
    1.01
    Activations Density 0.040%

    No Known Activations