© 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. 10-GEMMASCOPE-RES-131K
    7. 110633
    Prev
    Next
    INDEX
    Explanations

    teacher and farmer

    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_10/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
    s
    -3.66
     to
    -2.92
    휀
    -2.84
    ”
    -2.67
    u
    -2.55
    鋨
    -2.39
    
    -2.30
    }
    -2.27
    नलोड
    -2.22
    銩
    -2.20
    POSITIVE LOGITS
     When
    2.50
    It
    2.42
    時間も
    2.34
    ſelf
    2.33
    СЯ
    2.27
     упаковке
    2.23
     Когда
    2.20
    Depending
    2.19
    They
    2.16
     There
    2.14
    Activations Density 0.014%

    No Known Activations