© 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. 34-GEMMASCOPE-RES-131K
    7. 82462
    Prev
    Next
    INDEX
    Explanations

    ; and

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

    The neuron fires strongly on numeric identifiers (long numbers, section codes, years, or similarly formatted numeric strings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     (
    -1.27
     LIABLE
    -1.16
     just
    -1.10
     ولكن
    -1.08
     all
    -1.05
     But
    -1.05
     Viitattu
    -1.02
    <0xDE>
    -1.02
     gabbana
    -1.02
    eping
    -1.01
    POSITIVE LOGITS
     and
    3.55
     tevreden
    1.20
     heerlijk
    1.13
     voldoende
    1.13
    »;
    1.11
    ↵↵
    1.09
     verko
    1.09
    merkmale
    1.08
     sone
    1.05
     soutě
    1.05
    Activations Density 0.018%

    No Known Activations