© 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. 22-GEMMASCOPE-RES-131K
    7. 39066
    Prev
    Next
    INDEX
    Explanations

    negative concluding remarks

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

    This neuron flags strongly evaluative or intensity-laden words (adjectives and nouns) that convey emphasis or degree.

    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
     which
    -1.29
     però
    -1.00
     όμως
    -1.00
    ינוך
    -0.95
     nhưng
    -0.93
     squadre
    -0.93
     aufmerksam
    -0.91
     namun
    -0.90
     satuan
    -0.90
    지만
    -0.87
    POSITIVE LOGITS
     so
    1.69
     anyway
    1.25
     especially
    1.20
    Especially
    1.20
     particularmente
    1.06
     particularly
    1.05
     anyhow
    1.04
     particuli
    1.02
     So
    1.02
     especialmente
    1.01
    Activations Density 0.035%

    No Known Activations