© 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. 22-GEMMASCOPE-RES-131K
    4. 67891
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with function calls

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

    The neuron fires on standalone mathematical symbols—single‐letter variables, digits, and operators—i.e. the basic tokens of algebraic or arithmetic notation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ですが
    -1.42
     Grüßen
    -1.27
     процес
    -1.21
     almost
    -1.17
     after
    -1.17
     without
    -1.16
     intensely
    -1.12
    に対する
    -1.09
    w
    -1.09
     even
    -1.08
    POSITIVE LOGITS
    पि
    1.35
    了一個
    1.35
    dians
    1.30
    ittaa
    1.30
    袛
    1.24
    の時間
    1.21
    lograph
    1.20
     Giz
    1.20
    の詳細
    1.20
     discrepan
    1.19
    Activations Density 0.039%

    No Known Activations