© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 66983
    Prev
    Next
    INDEX
    Explanations

    Los Angeles

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

    The neuron strongly activates on subword tokens carrying apostrophes (contractions or elisions).

    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
    m
    -1.98
    );
    -1.78
     نیز
    -1.66
    n
    -1.66
     있으며
    -1.64
     of
    -1.64
    2
    -1.59
    },
    -1.56
    }$.
    -1.55
    9
    -1.55
    POSITIVE LOGITS
     its
    1.84
     maravillosa
    1.77
    푠
    1.70
    nữ
    1.54
     اولین
    1.52
     живут
    1.46
    闐
    1.44
    aceite
    1.41
     atend
    1.41
     könig
    1.41
    Activations Density 0.128%

    No Known Activations