© 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. 22-GEMMASCOPE-RES-131K
    4. 12772
    Prev
    Next
    INDEX
    Explanations

    mathematical symbolic expressions

    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
    <bos>
    -1.69
    などの
    -1.34
     TÉCNICA
    -1.16
     then
    -1.16
    などを
    -1.12
    ее
    -1.09
    を
    -1.06
    ॅ
    -1.03
    などが
    -1.02
     лай
    -1.02
    POSITIVE LOGITS
    えっ
    1.59
     chacune
    1.44
     завжди
    1.29
     Puts
    1.26
    んでしょう
    1.24
    carian
    1.23
    のですね
    1.22
    ៖
    1.20
     ചെയ
    1.20
     немає
    1.20
    Activations Density 0.012%

    No Known Activations