© 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. 35997
    Prev
    Next
    INDEX
    Explanations

    explanation or request for help

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

    The neuron fires on the answer-header lines denoted “A” followed by a large numeric token (the answer-length marker).

    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
    vereignty
    -1.55
    vereign
    -1.42
    fordshire
    -1.38
    😻
    -1.36
    farer
    -1.35
     venner
    -1.33
    thodoxy
    -1.32
    🤨
    -1.29
    》.
    -1.27
    phans
    -1.27
    POSITIVE LOGITS
     According
    1.41
    According
    1.35
     This
    1.34
     There
    1.33
     will
    1.28
     here
    1.23
     required
    1.16
    It
    1.11
     It
    1.10
     want
    1.09
    Activations Density 0.006%

    No Known Activations