© 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. 78155
    Prev
    Next
    INDEX
    Explanations

    TR/ in urls

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

    The neuron activates on numeric tokens—digits or digit‐based identifiers—such as version numbers, IDs, and other numeric codes in markup and server‐side directives.

    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
    Xt
    -0.74
    /*---
    -0.74
     psycopg
    -0.73
     descripcion
    -0.70
    graham
    -0.69
     Manager
    -0.68
    兇
    -0.66
    求め
    -0.65
     },
    -0.65
     Mun
    -0.65
    POSITIVE LOGITS
    ͝
    0.72
    ută
    0.69
    shuffle
    0.68
     الحكوم
    0.67
     hoodie
    0.65
    ByIndex
    0.64
    VertexBuffer
    0.64
    ensity
    0.64
     Vella
    0.63
     rowing
    0.63
    Activations Density 0.072%

    No Known Activations