© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38078
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    The neuron fires on numeric tokens—digits or multi‐digit numbers (e.g. counts, years, or other numeric figures).

    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
    χεία
    -0.81
     thought
    -0.78
    =[],
    -0.71
     iParam
    -0.70
     nem
    -0.70
    炬
    -0.69
    TC
    -0.69
    EditText
    -0.69
     express
    -0.68
    assen
    -0.68
    POSITIVE LOGITS
    melidir
    0.85
     goddamn
    0.82
     obstructing
    0.81
    angelog
    0.81
    vartheta
    0.78
     主题
    0.77
    Création
    0.75
    子供の
    0.75
     maji
    0.74
     Spoiler
    0.74
    Activations Density 0.016%

    No Known Activations