© 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. 10-GEMMASCOPE-RES-131K
    7. 113196
    Prev
    Next
    INDEX
    Explanations

    place names and descriptive words

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

    The neuron is primarily detecting place names and other geographic 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_10/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
     that
    -2.36
     or
    -2.03
    𝜔
    -1.91
     خوبه
    -1.80
    以上です
    -1.77
    ଶ
    -1.77
    𝜌
    -1.75
    谆
    -1.73
    ଵ
    -1.67
     σας
    -1.66
    POSITIVE LOGITS
     both
    1.65
    ଂ
    1.63
    ÈNE
    1.62
     two
    1.55
     jika
    1.53
    Während
    1.48
     trama
    1.42
     أيام
    1.41
     Pyrénées
    1.41
     RequestMethod
    1.40
    Activations Density 0.029%

    No Known Activations