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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79759
    Prev
    Next
    INDEX
    Explanations

    movement and connection

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

    The neuron fires on verbs in their past or past‐participle form (e.g. shaped, drawn, pulled, sculpted, showed).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     allarg
    -1.21
     размере
    -1.17
     -
    -1.13
     getrennt
    -1.11
    叭
    -1.08
    锇
    -1.07
    と思われます
    -1.06
    ৄ
    -1.04
     データ
    -1.02
    もある
    -1.02
    POSITIVE LOGITS
     and
    1.91
     out
    1.89
     from
    1.70
     through
    1.57
     into
    1.45
     the
    1.33
     across
    1.27
    ——”
    1.27
     LCCN
    1.25
     vanaf
    1.22
    Activations Density 0.054%

    No Known Activations