© 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. 116372
    Prev
    Next
    INDEX
    Explanations

    stub, stubbed, stubble, stubborn, stubs</div>

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

    The neuron fires on any token containing the substring “stub” (e.g. “stub,” “Stub,” “stubs”).

    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
     parentId
    -0.84
    seys
    -0.81
    Flor
    -0.78
     oreille
    -0.77
    ferien
    -0.76
     internationales
    -0.76
    Brick
    -0.75
     shoppers
    -0.74
     Akin
    -0.73
     mengenal
    -0.73
    POSITIVE LOGITS
     Stub
    1.27
    stub
    1.25
     stub
    1.21
     stubborn
    1.09
    Stub
    0.93
     Stubbs
    0.92
     Graz
    0.90
     }}{
    0.82
    ail
    0.81
     persistence
    0.81
    Activations Density 0.005%

    No Known Activations