© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38781
    Prev
    Next
    INDEX
    Explanations

    variables and operators

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

    The neuron fires on floating‐point numeric literals (i.e. numbers containing a decimal point).

    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
     Mersey
    -0.95
    วรร
    -0.93
    prüche
    -0.88
    сматри
    -0.84
     estric
    -0.84
    Msp
    -0.82
    规
    -0.81
    CIL
    -0.79
     representative
    -0.78
     Limited
    -0.78
    POSITIVE LOGITS
     esqueleto
    1.04
     diskusi
    0.97
     häm
    0.96
    presented
    0.93
     getIs
    0.93
     zarówno
    0.91
    himself
    0.91
    ࣭
    0.91
     telefonu
    0.90
     kebijakan
    0.89
    Activations Density 0.057%

    No Known Activations