© 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. 7291
    Prev
    Next
    INDEX
    Explanations

    SQL Server, bone strength, smoking withdrawal

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

    specialized technical terms related to computing, software, and technology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron highlights prominent domain-specific or proper-noun keywords (e.g. technology or subject names).

    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
    ſſen
    -1.71
     gouttes
    -1.68
    蚰
    -1.62
    苼
    -1.56
     exemplaires
    -1.55
    hidup
    -1.55
     ongles
    -1.54
     arbres
    -1.54
     Produit
    -1.51
     kimdir
    -1.51
    POSITIVE LOGITS
     and
    1.96
     its
    1.77
     also
    1.73
     Also
    1.70
    These
    1.69
    :
    1.66
     your
    1.50
     In
    1.45
    When
    1.43
     Its
    1.41
    Activations Density 0.605%

    No Known Activations