© 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. 34-GEMMASCOPE-RES-131K
    7. 331
    Prev
    Next
    INDEX
    Explanations

    children's book characters

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

    This neuron responds to structural cues marking section headers or title metadata (e.g. titles, series names, and other formal document-structure markers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    少年
    -0.88
    フォーマンス
    -0.79
     copper
    -0.78
    ould
    -0.78
     Nickelodeon
    -0.77
     הארץ
    -0.77
     manganese
    -0.76
     viewDidLoad
    -0.75
     orphanage
    -0.75
     orphan
    -0.73
    POSITIVE LOGITS
    Zdra
    0.87
     Viet
    0.72
    就不会
    0.71
    Varför
    0.70
    נס
    0.69
    })-\
    0.69
     رائعة
    0.68
    Overseas
    0.67
     感想
    0.65
    Ὑ
    0.65
    Activations Density 0.011%

    No Known Activations