© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116173
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

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

    This neuron detects occurrences of the identifier “Observer” in code.

    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
    "])
    -0.83
    lue
    -0.77
     flange
    -0.75
     subter
    -0.73
    Ser
    -0.71
    }}^{(
    -0.71
    =====
    -0.69
     progetti
    -0.68
     flexibility
    -0.68
     apaixon
    -0.67
    POSITIVE LOGITS
    nemone
    0.72
     Puff
    0.70
    BottomSheet
    0.69
    нка
    0.68
    られている
    0.66
    junct
    0.65
    suicide
    0.65
    won
    0.65
    Puff
    0.65
     Chelsea
    0.64
    Activations Density 0.033%

    No Known Activations