© 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. 68119
    Prev
    Next
    INDEX
    Explanations

    Sama, Sami, SAS, Paolo, Saudi, Galway

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

    This neuron responds whenever a token contains the letter sequence “sa” (in any case), e.g. SAS, sas, Sama, Saudi, etc.

    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
     This
    -4.28
     If
    -3.59
     You
    -3.34
     Now
    -3.30
    荩
    -3.08
     These
    -2.95
     Without
    -2.94
     ésta
    -2.92
     Then
    -2.89
     With
    -2.88
    POSITIVE LOGITS
    圌
    2.97
    EVERY
    2.84
     liquide
    2.83
    槼
    2.81
     刺繍
    2.78
    킁
    2.75
     soldat
    2.69
    麃
    2.67
    垟
    2.67
    titial
    2.67
    Activations Density 0.007%

    No Known Activations