© 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. 22-GEMMASCOPE-RES-131K
    7. 34403
    Prev
    Next
    INDEX
    Explanations

    recent past events

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

    This neuron fires on the first key content word that begins a new paragraph or major sentence—especially temporal or locational markers like “Five,” “When,” “In,” or “At.”

    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
    czegóły
    -1.28
    因为
    -1.27
    これは
    -1.26
    为了
    -1.20
    中学校
    -1.09
     vorhandenen
    -1.09
    を
    -1.08
    琬
    -1.08
     also
    -1.07
     is
    -1.06
    POSITIVE LOGITS
    Recently
    1.36
     recently
    1.30
     Time
    1.19
     recientemente
    1.16
     Você
    1.16
     parseFrom
    1.15
     dimentic
    1.14
     Recently
    1.13
     recent
    1.09
    Πηγή
    1.09
    Activations Density 0.107%

    No Known Activations