© 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. 54345
    Prev
    Next
    INDEX
    Explanations

    descriptive adjective-noun phrases

    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
     to
    -1.40
    crata
    -1.29
    以外の
    -1.27
    outros
    -1.27
    例句
    -1.26
    cnia
    -1.25
    其他
    -1.23
    UIFont
    -1.22
    razer
    -1.17
     anderen
    -1.16
    POSITIVE LOGITS
    <bos>
    1.48
    <0xA3>
    1.25
     fraî
    1.21
     applau
    1.20
     conster
    1.19
    </em>
    1.19
    thirds
    1.16
     nevo
    1.15
    說道
    1.10
     دریا
    1.09
    Activations Density 0.129%

    No Known Activations