© 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. 34-GEMMASCOPE-RES-131K
    7. 117591
    Prev
    Next
    INDEX
    Explanations

    conditions and disclaimer

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

    This neuron primarily fires on tokens that represent numbers or all‐caps identifiers (e.g. numeric literals, years, configuration keys like “AMPMS,” “DAY,” etc.).

    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
    azgo
    -0.78
    име
    -0.69
    assign
    -0.69
     Asn
    -0.67
     inhabit
    -0.66
    Cana
    -0.66
    Transform
    -0.66
    ans
    -0.65
     تض
    -0.65
     ireland
    -0.65
    POSITIVE LOGITS
    ými
    0.75
    robi
    0.74
    logna
    0.71
    éis
    0.69
    NEGATIVE
    0.69
     dumping
    0.69
    视图
    0.68
    絕
    0.68
     schnelle
    0.68
    blusa
    0.66
    Activations Density 0.031%

    No Known Activations