© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90236
    Prev
    Next
    INDEX
    Explanations

    judge and recorder

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     filed
    -0.84
     Anfield
    -0.81
     Bench
    -0.81
    Всего
    -0.79
    ξει
    -0.77
     filings
    -0.76
    EDF
    -0.76
     Magistrate
    -0.73
     entertained
    -0.73
     đáo
    -0.73
    POSITIVE LOGITS
     Recorder
    1.00
     crown
    0.84
    Recorder
    0.82
     opening
    0.81
    Opening
    0.79
    crown
    0.79
     recorder
    0.75
     Krone
    0.72
    Crown
    0.72
     señ
    0.70
    Activations Density 0.036%

    No Known Activations