© 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. 71856
    Prev
    Next
    INDEX
    Explanations

    also describes further actions

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

    This neuron specifically fires on the discourse marker “also” when used in formal technical or patent-style descriptions to introduce additional related features.

    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
     that
    -1.59
    がなく
    -1.48
     cewek
    -1.34
     Apalagi
    -1.32
    Transcripción
    -1.30
    кування
    -1.30
     Çok
    -1.29
     Çünkü
    -1.29
     Bagaimana
    -1.29
     手工
    -1.29
    POSITIVE LOGITS
    !
    1.91
    ☎️
    1.48
    randint
    1.48
     dientes
    1.48
     caballeros
    1.42
    ?
    1.41
     ‘
    1.38
     a
    1.36
    :],
    1.35
    Issue
    1.34
    Activations Density 0.068%

    No Known Activations