Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7726
    Prev
    Next
    INDEX
    Explanations

    bass, theme, remote, holding

    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_34/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
     aufgenommen
    -1.26
    際は
    -1.18
    際には
    -1.16
    ようで
    -1.13
     GmbH
    -1.08
    屋さん
    -1.02
    為に
    -1.02
    際に
    -1.00
     wtedy
    -1.00
     faldas
    -1.00
    POSITIVE LOGITS
    ฯ
    1.35
    などなど
    1.16
    呖
    1.08
    もしか
    1.05
    但这
    1.05
    窯
    1.03
    という感じ
    1.01
    適量
    1.00
    って思
    0.98
    と思ったら
    0.96
    Activations Density 0.495%

    No Known Activations