© 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. 34-GEMMASCOPE-RES-131K
    7. 47515
    Prev
    Next
    INDEX
    Explanations

    concealing within locations

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

    The main thing this neuron does is detect words describing hiding or concealing objects.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    tismo
    -1.02
    当时
    -0.91
    éroport
    -0.90
     onCancelled
    -0.88
    babkan
    -0.87
     oreja
    -0.87
    以后
    -0.83
    elab
    -0.83
     lorsqu
    -0.82
     iload
    -0.82
    POSITIVE LOGITS
     under
    3.64
     behind
    3.55
     between
    3.06
     underneath
    2.94
     beneath
    2.91
     inside
    2.69
    behind
    2.45
     debajo
    2.45
     on
    2.33
    under
    2.28
    Activations Density 0.101%

    No Known Activations