© 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. 106635
    Prev
    Next
    INDEX
    Explanations

    expressing necessity or obligation

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

    The neuron fires on personal pronouns (“I,” “you,” “we,” etc.) and emphatic adverbs (“just,” “absolutely,” “really,” “simply,” etc.), i.e. speaker-centered references and intensifiers.

    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
    liek
    -0.93
    caba
    -0.89
    merken
    -0.84
    ülle
    -0.80
    ြ
    -0.78
     actualización
    -0.78
    inkl
    -0.77
     sposo
    -0.75
    ApJ
    -0.75
    HAW
    -0.75
    POSITIVE LOGITS
     MUST
    2.09
     absolutely
    1.95
     HAD
    1.89
     HAVE
    1.84
     HAS
    1.68
    一定要
    1.65
    Absolutely
    1.59
     обязательно
    1.57
     unbedingt
    1.54
    absolutely
    1.54
    Activations Density 0.045%

    No Known Activations