© 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. 21480
    Prev
    Next
    INDEX
    Explanations

    Nokia phones and developers

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

    The neuron selectively fires on occurrences of the word “Nokia” (i.e. mentions of the Nokia brand name).

    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
    1
    -5.47
    2
    -4.56
    a
    -4.31
    5
    -4.09
    ).
    -4.06
    3
    -3.75
    7
    -3.69
    8
    -3.64
     
    -3.42
    A
    -3.36
    POSITIVE LOGITS
    鷙
    3.20
    sobí
    2.81
    鳯
    2.80
    蜴
    2.78
    昞
    2.72
     宣传
    2.70
    轆
    2.64
    ParameterLimits
    2.61
    鴒
    2.58
    骥
    2.56
    Activations Density 0.013%

    No Known Activations