© 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. 67225
    Prev
    Next
    INDEX
    Explanations

    private network, APIs, key, cloud, events

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

    The neuron is primarily responsive to occurrences of the word “private.”

    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
    '
    -4.28
    ↵↵
    -3.73
     “
    -3.36
    </strong>
    -3.33
     
    -3.30
    {
    -3.13
      
    -2.92
     are
    -2.84
    氿
    -2.81
    "
    -2.73
    POSITIVE LOGITS
    Даже
    3.34
    Despite
    3.34
    酲
    3.33
    Although
    3.22
    Surprisingly
    3.19
    Возможно
    3.17
    Following
    3.16
    Even
    3.16
    鋮
    3.16
    𓄹
    3.13
    Activations Density 0.014%

    No Known Activations