© 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. 12395
    Prev
    Next
    INDEX
    Explanations

    code declaration keywords

    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
     on
    -1.48
    宝物
    -1.39
     apartament
    -1.39
     also
    -1.35
    を
    -1.33
    が
    -1.31
     all
    -1.30
    があります
    -1.29
     kupa
    -1.28
    籐
    -1.27
    POSITIVE LOGITS
    為に
    1.44
     éprou
    1.42
    様な
    1.41
    久し
    1.39
     wtedy
    1.33
    にほんブログ村
    1.31
    あー
    1.27
    ほら
    1.24
    ことも
    1.23
     éte
    1.23
    Activations Density 0.019%

    No Known Activations