© 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. 585
    Prev
    Next
    INDEX
    Explanations

    number sequences

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

    This neuron consistently activates on numeric tokens (e.g. years, counts, or other digit sequences).

    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
     marginTop
    -1.09
     merusak
    -1.09
     minOccurs
    -1.00
    avut
    -1.00
    érial
    -0.98
    gonic
    -0.98
    amerikanischer
    -0.98
     inicial
    -0.97
    ométrique
    -0.96
     It
    -0.96
    POSITIVE LOGITS
     vlees
    1.08
     größe
    1.02
     denkt
    1.00
     verborgen
    0.98
     aktualisiert
    0.98
     and
    0.96
    oczes
    0.94
     "
    0.93
     our
    0.93
     präsenti
    0.92
    Activations Density 0.000%

    No Known Activations