© 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. 12542
    Prev
    Next
    INDEX
    Explanations

    Parameterized binding and localization

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

    programming code related to initialization, particularly focusing on instance variables, properties, or data loading.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     muñeco
    -1.18
     conejo
    -1.18
    乐观
    -1.12
     těchto
    -1.10
    Herm
    -1.07
     prostředí
    -1.02
     graciosas
    -1.01
    ξω
    -1.01
    Decrease
    -1.00
     erzeugen
    -0.99
    POSITIVE LOGITS
     and
    1.19
     again
    1.04
     们
    0.97
     if
    0.94
    ！！！！
    0.93
    a
    0.93
    …？
    0.93
     wieder
    0.93
    get
    0.92
     temperature
    0.92
    Activations Density 0.002%

    No Known Activations