© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66537
    Prev
    Next
    INDEX
    Explanations

    finding answers or conclusions

    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
     conoce
    -0.85
     ELSE
    -0.84
     ffs
    -0.81
    ัฒนา
    -0.79
     ✔️
    -0.79
    fähigkeit
    -0.78
    𝔾
    -0.77
     EXAMPLE
    -0.75
     denselben
    -0.75
    möglichkeiten
    -0.74
    POSITIVE LOGITS
     answer
    1.41
     Answer
    1.05
    answer
    1.03
    Answer
    1.01
    ANSWER
    0.96
     thankfully
    0.96
    実は
    0.89
     honestly
    0.87
    答案
    0.85
    結論
    0.85
    Activations Density 0.187%

    No Known Activations