© 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. 93100
    Prev
    Next
    INDEX
    Explanations

    posts and neighborhoods

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

    The neuron fires on multi‐digit numeric tokens (e.g. post counts, timestamps, IDs) in forum metadata.

    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
    resave
    -0.82
    ╡
    -0.79
     gently
    -0.75
    InputModule
    -0.74
     misst
    -0.73
     reduces
    -0.73
     Campionato
    -0.73
     newInstance
    -0.73
     Aéroport
    -0.73
     accidentally
    -0.73
    POSITIVE LOGITS
     neighbourhoods
    0.90
     neighbourhood
    0.88
     neighborhoods
    0.79
    tya
    0.79
     vetores
    0.78
     ranger
    0.78
     favoriser
    0.77
     neighborhood
    0.77
    kama
    0.77
     posts
    0.77
    Activations Density 0.005%

    No Known Activations