© 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. 22-GEMMASCOPE-RES-131K
    7. 27609
    Prev
    Next
    INDEX
    Explanations

    place names and institutions

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

    The neuron is responding to items in enumerations or list‐style sequences (e.g. names and entries in bulleted or tabular lists).

    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
    useNewUrlParser
    -1.34
    が違う
    -1.19
    providedIn
    -1.17
     médicaments
    -1.17
     frontières
    -1.16
    ᅚ
    -1.15
    ふと
    -1.15
     ausgewählt
    -1.13
    addCriterion
    -1.13
     needed
    -1.10
    POSITIVE LOGITS
     at
    1.65
     one
    1.24
     if
    1.17
     on
    1.16
     those
    1.16
     several
    1.16
     so
    1.13
     operar
    1.13
    当然是
    1.13
    協議
    1.09
    Activations Density 0.027%

    No Known Activations