© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102308
    Prev
    Next
    INDEX
    Explanations

    what's

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

    The neuron is detecting the "'s" suffix (the apostrophe-s form used in contractions and possessives).

    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
    geſ
    -2.30
    芣
    -2.25
    ⢊
    -2.13
     sportivo
    -2.11
    
    -2.08
    ႐
    -2.02
    烀
    -2.02
     Namun
    -1.96
     microns
    -1.94
    เตอร์
    -1.92
    POSITIVE LOGITS
    -
    3.44
    ↵↵
    3.16
    ↵
    1.94
     zahlreichen
    1.89
     been
    1.86
    \
    1.84
     I
    1.76
     
    1.67
     nahezu
    1.66
     i
    1.65
    Activations Density 0.006%

    No Known Activations