© 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. 9815
    Prev
    Next
    INDEX
    Explanations

    explanation or instruction

    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
     PROVIDE
    -1.20
     этих
    -1.20
    骉
    -1.14
     молодых
    -1.08
     solches
    -1.06
    这一幕
    -1.05
     тези
    -1.05
    outro
    -1.04
     Comme
    -1.02
    やう
    -1.02
    POSITIVE LOGITS
    šenie
    1.12
    ：
    1.05
    )--
    1.05
     its
    0.97
    ƅ
    0.95
    籟
    0.93
    ).....
    0.92
    密的
    0.91
    |--
    0.90
     €)
    0.90
    Activations Density 0.095%

    No Known Activations