© 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. 22-GEMMASCOPE-RES-131K
    7. 67735
    Prev
    Next
    INDEX
    Explanations

    configuration objects

    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
     its
    -1.77
     from
    -1.55
     ͡
    -1.50
     Both
    -1.50
     that
    -1.48
     nyeri
    -1.44
    になれる
    -1.34
    壟
    -1.31
    Our
    -1.27
    ﾈ
    -1.27
    POSITIVE LOGITS
     “
    1.65
     ‘
    1.30
    *
    1.23
    ...
    1.20
    '
    1.20
     phe
    1.14
    ‘
    1.14
    なので
    1.14
    “
    1.14
    <
    1.13
    Activations Density 0.010%

    No Known Activations