© 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. 67041
    Prev
    Next
    INDEX
    Explanations

    file paths and code snippets

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

    The neuron appears to be essentially inactive (it never responds to any token) and so doesn’t reliably detect any particular pattern.

    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
     time
    -2.19
     если
    -2.05
     an
    -1.97
     dobré
    -1.90
     kümmern
    -1.89
     various
    -1.88
    0
    -1.86
     different
    -1.83
     their
    -1.83
    懺
    -1.79
    POSITIVE LOGITS
    踯
    2.00
     😅
    1.92
    埽
    1.90
    たびに
    1.89
     groen
    1.87
     MICHAEL
    1.79
     priva
    1.77
     formid
    1.74
    齮
    1.72
     Autó
    1.71
    Activations Density 0.001%

    No Known Activations