© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124043
    Prev
    Next
    INDEX
    Explanations

    public class declarations

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

    The neuron primarily detects numeric literal tokens in source code (e.g. integer or floating‐point constants).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    standigheden
    -1.43
    陝
    -1.40
     BERNAMA
    -1.36
    ло
    -1.35
     yzf
    -1.34
    $
    -1.30
     lmfao
    -1.30
    IRIT
    -1.27
    𝑈
    -1.27
    哪
    -1.25
    POSITIVE LOGITS
    t
    1.79
     promesse
    1.59
     You
    1.56
    Poids
    1.47
     réputation
    1.44
     marred
    1.38
     ravaged
    1.38
    TryDecode
    1.38
    iedz
    1.36
    鉭
    1.36
    Activations Density 0.012%

    No Known Activations