© 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. 34-GEMMASCOPE-RES-131K
    4. 55698
    Prev
    Next
    INDEX
    Explanations

    enough something

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

    The neuron fires on occurrences of the word “enough.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    itisation
    -1.52
    罍
    -1.41
    eding
    -1.40
    盉
    -1.35
    uristic
    -1.35
    heds
    -1.34
    gives
    -1.31
     carcasa
    -1.27
     klien
    -1.27
    יצוב
    -1.24
    POSITIVE LOGITS
     of
    4.19
     to
    2.25
     people
    1.66
     for
    1.41
     from
    1.30
     tries
    1.30
     information
    1.28
     in
    1.16
     time
    1.13
     on
    1.12
    Activations Density 0.007%

    No Known Activations