© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84754
    Prev
    Next
    INDEX
    Explanations

    is known, described, shot

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

    This neuron primarily detects numeric tokens and numerical values (e.g. figure numbers, measurements, dates, quantities).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    只需
    -1.23
    ⽼
    -1.18
    where
    -1.17
     lượng
    -1.11
    拉着
    -1.06
     certamente
    -1.05
    !<
    -1.04
     frequent
    -1.04
     rispondere
    -1.04
     unlike
    -1.03
    POSITIVE LOGITS
    šanas
    1.13
     אני
    1.09
    ācija
    1.09
    1.07
    либо
    1.05
    begin
    1.05
     which
    1.05
     Institutionen
    1.04
     mulai
    1.02
    vací
    1.02
    Activations Density 0.150%

    No Known Activations