© 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. 10-GEMMASCOPE-RES-131K
    7. 10223
    Prev
    Next
    INDEX
    Explanations

    rant

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

    The neuron spots instances of “rant”-style words indicating a complaint or tirade (e.g. “rant,” “rave,” “ramblings”).

    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
    蛧
    -2.94
    戩
    -2.69
     ส์
    -2.69
    ஂ
    -2.56
    
    -2.23
    yskland
    -2.23
     }
    -2.23
    獃
    -2.22
     enforce
    -2.19
    เกง
    -2.19
    POSITIVE LOGITS
    餮
    2.64
     défis
    2.36
    硨
    2.27
    ↵↵
    2.25
     obligatory
    2.14
     varsa
    2.11
    妧
    2.11
     estadounidenses
    2.11
    퀼
    2.05
    昳
    2.05
    Activations Density 0.002%

    No Known Activations