© 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. 34-GEMMASCOPE-RES-131K
    7. 47914
    Prev
    Next
    INDEX
    Explanations

    actions and processes

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

    The neuron flags numeric‐heavy, data‐reporting contexts—multi‐digit figures, commas, and related tokens in statistical or quantified passages.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     clockwise
    -0.81
     chameleon
    -0.74
     Camilla
    -0.73
     interchangeably
    -0.73
     posthum
    -0.73
     GG
    -0.73
    álja
    -0.71
     يريد
    -0.71
    eddable
    -0.70
    Probl
    -0.69
    POSITIVE LOGITS
     operate
    1.23
    operate
    1.10
     operating
    1.05
     hacerlo
    1.03
     operates
    1.00
     erfolgt
    0.98
     operated
    0.91
     melakukannya
    0.88
     done
    0.88
    operating
    0.87
    Activations Density 0.257%

    No Known Activations