© 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. 39853
    Prev
    Next
    INDEX
    Explanations

    organizational activities, tasks

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

    The neuron fires on any occurrence of the word “activity” or “activities,” detecting that specific term wherever it appears.

    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
    ي
    -2.61
    ار
    -2.47
    ⟐
    -2.33
    い
    -2.28
     เมื่อ
    -2.27
    𐐪
    -2.22
    鶚
    -2.17
    ه
    -2.16
    </b>
    -2.14
     et
    -2.14
    POSITIVE LOGITS
    </h3>
    2.64
    m
    2.47
    was
    2.42
    y
    2.39
    蕻
    2.27
     dags
    2.19
     activities
    2.16
    at
    2.16
    狷
    2.14
    ஂ
    2.14
    Activations Density 0.008%

    No Known Activations