© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128749
    Prev
    Next
    INDEX
    Explanations

    column names and data entries

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

    The neuron detects numeric literals (numbers and numerical values) in the text.

    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
     et
    -1.03
     LIGHTS
    -1.02
     cerca
    -1.00
    complain
    -0.98
    osoba
    -0.96
    ud
    -0.94
    )=\
    -0.94
     犬
    -0.93
     «
    -0.93
     và
    -0.93
    POSITIVE LOGITS
     with
    1.30
     migliorare
    1.27
    じっくり
    1.25
     other
    1.19
     aiutare
    1.17
     entsprechenden
    1.16
    见的
    1.13
    Also
    1.10
    ógica
    1.10
     Ausführungen
    1.09
    Activations Density 0.068%

    No Known Activations