© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110632
    Prev
    Next
    INDEX
    Explanations

    thrown, Yorkshire locations, ride, section

    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
    conector
    -0.90
     bijvoorbeeld
    -0.85
    ῤ
    -0.84
    ただし
    -0.83
    ショナル
    -0.81
    unuz
    -0.81
    ियम
    -0.80
     Vì
    -0.79
     kirj
    -0.79
    toria
    -0.76
    POSITIVE LOGITS
     celebrates
    0.96
     but
    0.91
     природа
    0.90
    բ
    0.88
    霉
    0.85
     UNC
    0.79
    =('
    0.78
    Certifications
    0.77
    換え
    0.75
    <0xBA>
    0.74
    Activations Density 0.001%

    No Known Activations