© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74377
    Prev
    Next
    INDEX
    Explanations

    purpose or point

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

    This neuron detects perfect‐progressive constructions expressing audience anticipation (e.g. “have been waiting” or “been waiting for”).

    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
     because
    -1.71
     through
    -1.66
     as
    -1.66
     thru
    -1.40
     under
    -1.38
     in
    -1.36
     name
    -1.36
     soportar
    -1.35
     the
    -1.34
     numerosas
    -1.33
    POSITIVE LOGITS
     indepen
    1.43
     legendar
    1.37
     lamentable
    1.35
    にしました
    1.34
     uan
    1.29
     legiti
    1.28
     sabi
    1.28
     inconce
    1.27
     immor
    1.27
     iny
    1.27
    Activations Density 0.043%

    No Known Activations