© 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. 15118
    Prev
    Next
    INDEX
    Explanations

    positional change or movement

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

    The neuron specializes in detecting spatial or directional words and prepositions (e.g. down, upwards, into, along, through, round, forward, backwards) that describe movement or orientation.

    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
     naquele
    -1.27
    //
    -1.25
     then
    -1.24
    rians
    -1.24
     meantime
    -1.20
     circumstances
    -1.15
     للع
    -1.13
    彆
    -1.13
    組み立て
    -1.13
     completamente
    -1.12
    POSITIVE LOGITS
     these
    1.37
     kommentar
    1.35
     people
    1.34
     ikke
    1.32
     preocu
    1.30
    我们的
    1.24
     ваша
    1.23
     nuestras
    1.23
     our
    1.23
    щаться
    1.20
    Activations Density 0.113%

    No Known Activations