© 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. 12195
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with "*"

    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
     both
    -1.71
     сильно
    -1.38
    넛
    -1.31
     mainly
    -1.29
     ролях
    -1.28
     keduanya
    -1.27
     within
    -1.26
     mostly
    -1.22
    主に
    -1.22
     as
    -1.20
    POSITIVE LOGITS
    んでる
    1.49
     breathtaking
    1.42
     vinculados
    1.39
     VERY
    1.35
     stehe
    1.35
     quintessential
    1.34
    に行って
    1.33
     더
    1.32
    的心情
    1.32
     soooo
    1.31
    Activations Density 0.002%

    No Known Activations