© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 27687
    Prev
    Next
    INDEX
    Explanations

    make arguments

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

    The neuron is looking for formal argumentative cues—content words and markers (like parenthetical list numbers, discourse connectives such as “because” or “however,” and key nouns/verbs) that signal structured, academic or policy-style argumentation.

    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
    踔
    -1.21
    لع
    -1.09
    遑
    -1.09
     vilka
    -1.06
     dormitorios
    -1.06
     chrétien
    -1.06
    分野
    -1.03
    割合
    -1.02
     Relig
    -1.02
     hilsen
    -1.01
    POSITIVE LOGITS
     previous
    1.41
     arguments
    1.30
    Previous
    1.25
     precedent
    1.23
     argument
    1.23
     Previous
    1.22
    が無い
    1.18
     argue
    1.13
     risk
    1.11
     argued
    1.11
    Activations Density 0.035%

    No Known Activations