© 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. 93345
    Prev
    Next
    INDEX
    Explanations

    words starting with der

    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
     It
    -2.58
    豋
    -2.52
    ஂ
    -2.50
    Ⲉ
    -2.44
    廰
    -2.31
    鑁
    -2.30
    ឵
    -2.30
    鋱
    -2.23
    䊏
    -2.23
    普通的
    -2.20
    POSITIVE LOGITS
    ﺐ
    2.63
    $,
    2.61
    \
    2.58
    щиеся
    2.47
    狆
    2.30
     Şubat
    2.28
     empie
    2.25
    箆
    2.19
    ”.
    2.19
     交換
    2.16
    Activations Density 0.019%

    No Known Activations