© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35885
    Prev
    Next
    INDEX
    Explanations

    concluding a statement

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

    The neuron flags salient content‐bearing words—key nouns, verbs, and pronouns that carry the main meaning of the 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_22/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
    嘿嘿
    -0.90
     IMPLICATIONS
    -0.79
    initialState
    -0.78
    Uwaga
    -0.73
     keç
    -0.73
    bolso
    -0.72
     Organización
    -0.71
    iksi
    -0.71
    perd
    -0.71
     tải
    -0.70
    POSITIVE LOGITS
     goodbye
    1.49
     concludes
    1.34
     farewell
    1.28
     conclude
    1.27
     concluding
    1.23
     Thank
    1.04
    Goodnight
    1.04
     concluded
    1.02
     tomorrow
    1.01
     Goodbye
    1.01
    Activations Density 0.015%

    No Known Activations