© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93068
    Prev
    Next
    INDEX
    Explanations

    telephone calls

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

    The neuron is responding to numeric tokens—standalone numbers, percentages, or other quantitative figures.

    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
     these
    -1.27
     then
    -1.23
     ristorante
    -1.16
    llywood
    -1.16
     each
    -1.16
     those
    -1.14
    alucía
    -1.13
     both
    -1.12
    していない
    -1.11
    providedIn
    -1.05
    POSITIVE LOGITS
     gingen
    1.15
    了一眼
    1.15
    },$
    1.14
     opciones
    1.13
    Interesting
    1.08
    Haben
    1.06
    "}"
    1.06
     olika
    1.05
    وقد
    1.03
    Everything
    1.02
    Activations Density 0.000%

    No Known Activations