© 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. 13443
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

    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>
    -2.05
    などを
    -1.91
    などの
    -1.74
    があり
    -1.64
    を
    -1.61
    などが
    -1.59
    そして
    -1.57
    ちなみに
    -1.55
    つまり
    -1.55
    ebly
    -1.53
    POSITIVE LOGITS
     like
    1.43
    ようです
    1.42
    為に
    1.38
     it
    1.38
    にします
    1.27
    の準備
    1.27
    必要がある
    1.23
    好用
    1.22
    様な
    1.20
    ごとの
    1.20
    Activations Density 0.017%

    No Known Activations