© 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. 30717
    Prev
    Next
    INDEX
    Explanations

    variable assignment and comparison

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

    This neuron fires on unusually high-index (i.e. rare) tokens—effectively picking out low-frequency or uncommon identifiers and literals.

    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
    larımız
    -1.03
    ὑ
    -0.99
     ſont
    -0.94
    mutter
    -0.93
    ρία
    -0.92
     moeten
    -0.89
     aerolí
    -0.89
    Ѻ
    -0.88
     télécharge
    -0.87
    tagez
    -0.86
    POSITIVE LOGITS
     is
    2.33
     ==
    2.05
     isn
    1.86
     was
    1.73
    hasOwnProperty
    1.63
     !=
    1.54
     wasn
    1.45
    ==
    1.45
     exists
    1.43
     Is
    1.42
    Activations Density 0.020%

    No Known Activations