© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11744
    Prev
    Next
    INDEX
    Explanations

    frankly speaking or opinion

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

    The main thing this neuron does is detect the adverb “frankly.”

    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
    {
    -2.64
     such
    -2.25
     to
    -2.25
    ){
    -2.16
    </th>
    -2.16
     принцип
    -2.16
    istocene
    -2.14
     a
    -2.14
     of
    -2.08
     was
    -2.06
    POSITIVE LOGITS
    8
    3.00
    1
    2.97
    7
    2.92
    0
    2.88
    5
    2.77
    6
    2.53
    3
    2.53
    4
    2.44
    Until
    2.17
    If
    2.14
    Activations Density 0.002%

    No Known Activations