© 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. 110515
    Prev
    Next
    INDEX
    Explanations

    my current assessment

    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
     visse
    -1.52
     SqlDbType
    -1.47
    ⒈
    -1.46
    diode
    -1.44
    𓆉
    -1.44
    ניין
    -1.43
     এবং
    -1.43
    ulates
    -1.41
     tegas
    -1.40
     erns
    -1.40
    POSITIVE LOGITS
     from
    1.59
     that
    1.36
     seems
    1.27
     why
    1.27
     appears
    1.27
     gestartet
    1.24
    ang
    1.22
    ”
    1.20
     verfügb
    1.20
     использу
    1.19
    Activations Density 0.030%

    No Known Activations