© 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. 27822
    Prev
    Next
    INDEX
    Explanations

    locations followed by dates

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

    This neuron detects capitalized named entities, particularly geographic place names (and related proper nouns).

    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
    を行い
    -1.31
     and
    -1.18
     dabei
    -1.16
     a
    -1.13
    場合は
    -1.09
    mathrm
    -1.07
    ごとに
    -1.05
     Coupé
    -1.02
     плохо
    -1.02
     Templ
    -1.02
    POSITIVE LOGITS
     January
    1.46
     December
    1.41
     during
    1.38
     July
    1.33
     June
    1.32
     on
    1.32
     August
    1.31
    ignée
    1.31
     October
    1.30
    ญี่ป
    1.30
    Activations Density 0.146%

    No Known Activations