© 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. 75682
    Prev
    Next
    INDEX
    Explanations

    asking for or giving opinions

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

    The neuron strongly responds to the word “from” (especially when used in “straight from” or similar source-introducing phrases).

    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
     in
    -1.63
     pentru
    -1.48
     it
    -1.45
     для
    -1.45
    >
    -1.36
     we
    -1.34
    |
    -1.34
     We
    -1.30
     если
    -1.27
     suas
    -1.27
    POSITIVE LOGITS
     about
    1.73
     eléct
    1.46
     取り付け
    1.41
     bluz
    1.38
     薬局
    1.36
     récon
    1.35
     indiví
    1.34
     amortecedor
    1.34
    𝑊
    1.33
     維
    1.32
    Activations Density 0.062%

    No Known Activations