© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93420
    Prev
    Next
    INDEX
    Explanations

    positive statements and endorsements

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

    The neuron detects positive evaluative language expressing approval or a welcoming tone.

    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
    ándote
    -1.16
    capai
    -1.13
     during
    -1.11
    міні
    -1.09
     vanske
    -1.08
    PostExecute
    -1.05
    🪒
    -1.05
    совет
    -1.05
     soupe
    -1.02
     utford
    -1.02
    POSITIVE LOGITS
     endlich
    1.44
    可惜
    1.29
     it
    1.29
    终于
    1.20
     Teig
    1.20
     Endlich
    1.11
     finalmente
    1.11
     initiative
    1.10
     correctly
    1.10
     hopefully
    1.09
    Activations Density 0.022%

    No Known Activations