© 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. 7055
    Prev
    Next
    INDEX
    Explanations

    direction

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

    The neuron detects occurrences of “direction”‐related tokens (e.g. Direction, direction, Dir, Side).

    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
     respectivas
    -1.62
     sogenannten
    -1.48
     einzigen
    -1.46
     worldwide
    -1.38
     until
    -1.36
     mogą
    -1.34
     that
    -1.34
     Wurzeln
    -1.32
    なども
    -1.30
     colleagues
    -1.28
    POSITIVE LOGITS
     menyen
    1.96
     kreatif
    1.84
     française
    1.66
     aktivi
    1.65
     kommunik
    1.61
     sinyal
    1.57
     aktive
    1.53
     étudi
    1.52
     signifikan
    1.52
     direction
    1.48
    Activations Density 0.051%

    No Known Activations