© 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. 73586
    Prev
    Next
    INDEX
    Explanations

    php code openers

    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
     as
    -2.28
     have
    -2.28
    <bos>
    -2.25
    </h2>
    -2.14
     including
    -2.08
     using
    -2.03
     It
    -2.00
     just
    -1.99
     in
    -1.98
     by
    -1.98
    POSITIVE LOGITS
    {
    2.81
    殽
    2.52
    ons
    2.11
    ඍ
    2.08
    為に
    2.08
    さぁ
    2.03
    すっ
    2.00
    ley
    1.95
     IRELAND
    1.94
    釹
    1.94
    Activations Density 0.009%

    No Known Activations