© 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. 99644
    Prev
    Next
    INDEX
    Explanations

    non-volatile, Nevada state abbreviation

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

    The neuron primarily activates on occurrences of the token “NV.”

    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
    ⩩
    -2.86
    鋮
    -2.75
    隄
    -2.75
    墬
    -2.73
    ”;
    -2.72
     [])
    -2.67
    друг
    -2.67
    utterstock
    -2.66
    ”)
    -2.63
     ''),
    -2.59
    POSITIVE LOGITS
     —
    2.58
    —"
    2.52
     '
    2.47
    !"
    2.41
     dopo
    2.36
     he
    2.31
    ра
    2.27
    <bos>
    2.25
    跛
    2.23
    ",
    2.22
    Activations Density 0.004%

    No Known Activations