© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27679
    Prev
    Next
    INDEX
    Explanations

    initial tokens followed by punctuation

    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
    providedIn
    -1.50
     eerste
    -1.38
    瘊
    -1.26
    聍
    -1.25
    了出去
    -1.24
     EconPapers
    -1.22
    felpa
    -1.22
    
    -1.22
    了解更多
    -1.21
    谖
    -1.18
    POSITIVE LOGITS
     it
    1.48
    What
    1.24
    ٩
    1.07
    <
    1.05
    bringung
    1.05
    Another
    1.03
     possib
    1.03
    möglichen
    1.02
    Just
    1.02
    いても
    1.02
    Activations Density 0.000%

    No Known Activations