© 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. 65381
    Prev
    Next
    INDEX
    Explanations

    tempted to

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

    The neuron detects occurrences of the root “tempt” in any of its inflected or extended forms (e.g., tempt, tempted, tempting, temptress).

    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
    但
    -2.52
    對於
    -2.45
    で
    -2.36
    in
    -2.31
    er
    -2.28
     selben
    -2.27
                
    -2.20
    ,’”
    -2.14
     Ähnliche
    -2.14
     ‘‘
    -2.13
    POSITIVE LOGITS
    自己的
    2.56
    躄
    2.33
    ౭
    2.33
    媜
    2.30
    耵
    2.27
    沨
    2.25
    ственном
    2.20
    俛
    2.19
    垟
    2.19
    埽
    2.16
    Activations Density 0.001%

    No Known Activations