© 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. 34-GEMMASCOPE-RES-131K
    7. 77449
    Prev
    Next
    INDEX
    Explanations

    is important

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

    This neuron fires on copular evaluation phrases that assert importance or criticality (e.g. “X is important,” “X is critical,” “X is highly desirable”).

    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
     què
    -1.19
    ceptable
    -0.99
    รวจ
    -0.99
    mær
    -0.98
     possíveis
    -0.98
    merken
    -0.94
    ølge
    -0.93
    tungen
    -0.89
     teknis
    -0.89
    ėjimo
    -0.88
    POSITIVE LOGITS
     important
    7.00
    important
    5.22
     crucial
    5.16
    重要
    4.53
    Important
    4.50
     Important
    4.50
     vital
    4.44
     중요
    4.41
     importante
    4.41
     важ
    4.09
    Activations Density 0.420%

    No Known Activations