© 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. 34-GEMMASCOPE-RES-131K
    7. 107139
    Prev
    Next
    INDEX
    Explanations

    job duties and responsibilities

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

    The neuron fires on structural elements of the document—section headings, subheadings, and their punctuation—rather than ordinary running 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_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
    Въ
    -0.94
     воспользоваться
    -0.89
    Ҩ
    -0.86
    venske
    -0.85
    vability
    -0.84
    ἓ
    -0.84
     Finish
    -0.83
    žiť
    -0.82
    mentação
    -0.81
    omalainen
    -0.80
    POSITIVE LOGITS
     duties
    4.72
     respon
    4.53
     tasks
    3.53
     responsibility
    3.33
     Duties
    3.08
     role
    2.91
    Duties
    2.80
    Responsibilities
    2.70
     roles
    2.67
    tasks
    2.58
    Activations Density 0.068%

    No Known Activations