© 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. 10-GEMMASCOPE-RES-131K
    7. 74748
    Prev
    Next
    INDEX
    Explanations

    due to explaining reasons

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

    The neuron activates on numeric expressions, especially decimal numbers and ranges (e.g. “Due 113 to 260,” “37.5,” “110.5 to 256”).

    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
     when
    -2.14
     what
    -1.96
     new
    -1.94
     two
    -1.85
    </i>
    -1.76
    d
    -1.71
     one
    -1.70
     use
    -1.69
     takes
    -1.69
     is
    -1.68
    POSITIVE LOGITS
    裥
    2.02
     télécharger
    1.90
     interesses
    1.88
    僰
    1.84
    鹩
    1.83
    躄
    1.82
     perſ
    1.77
    趼
    1.77
    蚰
    1.77
    
    1.76
    Activations Density 0.024%

    No Known Activations