© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32625
    Prev
    Next
    INDEX
    Explanations

    south or bottom position

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

    The neuron fires on words or phrases that denote compass directions or geographical orientation (e.g. “southern,” “south of,” “northern,” etc.).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    sandalia
    -1.19
    //...
    -1.18
     sogen
    -1.07
    Deleting
    -1.07
    sobre
    -1.02
     towering
    -1.02
     высокая
    -1.01
    swiss
    -0.98
    次代
    -0.98
     numerosas
    -0.97
    POSITIVE LOGITS
     below
    1.27
    bottom
    1.26
     lows
    1.21
     bottom
    1.19
     Below
    1.18
     poniżej
    1.17
    ⬇
    1.09
     вниз
    1.07
    Down
    1.05
    LowerCase
    1.05
    Activations Density 0.136%

    No Known Activations