© 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. 99525
    Prev
    Next
    INDEX
    Explanations

    own + specific characteristics

    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
    ቍ
    -1.82
    栳
    -1.76
    ꪔ
    -1.63
    蠵
    -1.61
    ࿊
    -1.61
    毉
    -1.59
     potret
    -1.58
    
    -1.55
    тала
    -1.54
    ：“
    -1.52
    POSITIVE LOGITS
     something
    1.74
    呖
    1.74
     your
    1.69
     various
    1.62
     and
    1.59
     what
    1.59
    </h3>
    1.58
     是否
    1.53
     own
    1.47
     companies
    1.45
    Activations Density 0.009%

    No Known Activations