© 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. 22-GEMMASCOPE-RES-131K
    7. 79868
    Prev
    Next
    INDEX
    Explanations

    received a call

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

    The neuron strongly activates on punctuation tokens—especially commas, periods, and exclamation marks—i.e. it detects sentence‐boundary or strong punctuation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     TRY
    -1.04
    錞
    -1.01
     Users
    -1.01
     spektak
    -1.00
    已经
    -1.00
     månader
    -1.00
     Benutzer
    -0.99
    Patients
    -0.96
    Doctors
    -0.96
     jsPsych
    -0.95
    POSITIVE LOGITS
     receive
    1.34
     they
    1.33
     someone
    1.22
     there
    1.19
     was
    1.15
     asked
    1.08
     received
    1.06
     được
    1.05
     receber
    1.02
     nunca
    1.01
    Activations Density 0.017%

    No Known Activations