© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 543
    Prev
    Next
    INDEX
    Explanations

    temporal and scope adjectives with abstract nouns

    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
     when
    -1.89
     because
    -1.83
     with
    -1.55
    entukan
    -1.41
     penyanyi
    -1.41
    savevideo
    -1.40
     Warszawie
    -1.39
    cesta
    -1.39
    savevideobot
    -1.39
    мне
    -1.38
    POSITIVE LOGITS
    <em>
    1.43
    8
    1.42
     teuer
    1.41
    us
    1.39
     tiefer
    1.38
     любые
    1.37
     erwor
    1.36
    身邊
    1.35
    tion
    1.34
    <code>
    1.34
    Activations Density 0.384%

    No Known Activations