© 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. 42333
    Prev
    Next
    INDEX
    Explanations

    class-dump output

    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_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
    瑨
    -2.25
    砗
    -2.23
     itſelf
    -2.22
    uteurs
    -2.08
    ﻊ
    -2.06
    
    -2.03
    骓
    -2.02
    蜮
    -1.98
     mélang
    -1.98
    preneurs
    -1.98
    POSITIVE LOGITS
    2
    3.23
    0
    2.97
    at
    2.94
    9
    2.69
    4
    2.64
    ">
    2.61
    .”
    2.53
    _
    2.52
    7
    2.50
    3
    2.47
    Activations Density 0.063%

    No Known Activations