© 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. 98375
    Prev
    Next
    INDEX
    Explanations

    exclusion

    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
     สาว
    -0.82
    洽
    -0.81
     Quill
    -0.81
    FU
    -0.81
     AMERIC
    -0.80
    所需的
    -0.79
    וקר
    -0.78
     asker
    -0.77
    Yen
    -0.75
     النه
    -0.75
    POSITIVE LOGITS
     only
    2.13
     ONLY
    2.09
    ONLY
    2.06
    only
    1.96
     uniquement
    1.91
     только
    1.91
     فقط
    1.88
     тільки
    1.66
    Only
    1.63
     Only
    1.59
    Activations Density 0.236%

    No Known Activations