© 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. 72523
    Prev
    Next
    INDEX
    Explanations

    writing, style, clarity, voice

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

    The neuron fires most strongly on longer, morphologically complex content words (e.g. technical nouns and adjectives).

    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
     for
    -1.49
    othed
    -1.04
    hoots
    -1.03
    odzi
    -1.02
     with
    -1.02
    hopped
    -1.00
     vorn
    -0.99
     "..\..\
    -0.98
    titud
    -0.98
     dentro
    -0.98
    POSITIVE LOGITS
     aquellos
    1.29
    那些
    1.26
    Fordítás
    1.25
     August
    1.24
    icznych
    1.24
     September
    1.22
     размере
    1.20
    STRUCTION
    1.20
     December
    1.19
    庚
    1.18
    Activations Density 0.112%

    No Known Activations