© 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. 10-GEMMASCOPE-RES-131K
    4. 226
    Prev
    Next
    INDEX
    Explanations

    names and acronyms

    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
    </strong>
    -3.75
    genodigd
    -3.42
    饪
    -3.39
     tienden
    -3.22
    鸸
    -3.16
    </h3>
    -3.13
    
    -3.06
    蛲
    -2.98
    皷
    -2.98
     cheia
    -2.97
    POSITIVE LOGITS
    If
    4.06
    When
    3.88
    It
    3.83
    from
    3.80
    to
    3.67
    just
    3.59
    There
    3.38
    when
    3.38
    While
    3.25
    He
    3.20
    Activations Density 0.022%

    No Known Activations