© 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. 22-GEMMASCOPE-RES-131K
    7. 54398
    Prev
    Next
    INDEX
    Explanations

    sqlite database usage

    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_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
    d
    -2.22
     This
    -2.22
     That
    -2.19
    </b>
    -2.09
     From
    -1.94
     We
    -1.86
    9
    -1.77
     With
    -1.76
     Once
    -1.73
     Maybe
    -1.73
    POSITIVE LOGITS
    replyreport
    1.90
    ９
    1.82
    
    1.80
    WRENCE
    1.80
    釓
    1.77
    ﻒ
    1.75
    ዡ
    1.73
    ではまた
    1.72
    Ace
    1.70
    ❎
    1.70
    Activations Density 0.012%

    No Known Activations