© 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. 34-GEMMASCOPE-RES-131K
    7. 106667
    Prev
    Next
    INDEX
    Explanations

    End of descriptive phrases

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

    The neuron responds to sentence-ending punctuation marks (especially periods and exclamation points).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    😶
    -1.43
    -¡
    -1.36
    😖
    -1.35
    😑
    -1.30
    😐
    -1.30
    -_-
    -1.30
    ☹
    -1.26
     
    -1.22
    😒
    -1.21
    MAZ
    -1.19
    POSITIVE LOGITS
     this
    2.33
     also
    1.94
     close
    1.76
     lots
    1.73
     only
    1.73
     plenty
    1.73
     easy
    1.60
     come
    1.57
     comes
    1.54
     huge
    1.54
    Activations Density 0.013%

    No Known Activations