© 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. 22-GEMMASCOPE-RES-131K
    4. 11353
    Prev
    Next
    INDEX
    Explanations

    at or by the time

    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
    そして
    -1.38
     also
    -1.24
    參考文獻
    -1.17
    と
    -1.15
    や
    -1.13
    <bos>
    -1.10
     Grüßen
    -1.05
    便捷
    -1.03
    y
    -1.03
    もちろん
    -1.02
    POSITIVE LOGITS
    corrhi
    1.47
    為に
    1.46
     you
    1.46
    際には
    1.40
    際は
    1.37
     dimentic
    1.36
    方がいい
    1.32
    感じが
    1.31
    appellant
    1.31
    ところに
    1.30
    Activations Density 0.006%

    No Known Activations