© 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. 20989
    Prev
    Next
    INDEX
    Explanations

    comparison between items

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

    The neuron reliably fires on the preposition “between,” i.e. it detects instances of “between” used to link or compare two items.

    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
     
    -2.84
    餮
    -2.67
     seine
    -2.61
    や
    -2.56
    </b>
    -2.50
    —
    -2.50
    ’
    -2.50
    ли
    -2.45
    thschild
    -2.42
     одной
    -2.38
    POSITIVE LOGITS
     видит
    2.69
     Then
    2.59
    ابراین
    2.52
     cinquième
    2.47
     quatrième
    2.44
    ayaquil
    2.44
    㐂
    2.39
    也将
    2.38
    pecabe
    2.34
    nachron
    2.34
    Activations Density 0.063%

    No Known Activations