© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15940
    Prev
    Next
    INDEX
    Explanations

    our, Tucker, Most, So, Always, Explore, Maine

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

    lists of help resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tendencias
    0.48
     極
    0.45
    ยัง
    0.42
     inquis
    0.42
    тному
    0.42
     うる
    0.41
    考え
    0.40
    ゴ
    0.40
     inefficiency
    0.40
     確認
    0.40
    POSITIVE LOGITS
     ​
    0.51
    .​
    0.49
    ​
    0.46
    ​.
    0.45
     Improvement
    0.45
    .​​
    0.45
    、​
    0.43
    ller
    0.43
    रिमेंट
    0.42
    潦
    0.42
    Activations Density 0.070%

    No Known Activations