© 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. 34-GEMMASCOPE-RES-131K
    4. 109716
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases

    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
    Disc
    -0.80
    rüstung
    -0.78
    ņi
    -0.78
     ав
    -0.76
    offsetX
    -0.76
    熄
    -0.75
     シ
    -0.75
     הא
    -0.75
    olas
    -0.75
     กระ
    -0.74
    POSITIVE LOGITS
    ᚹ
    0.98
    身后的
    0.95
    极致
    0.95
    蹇
    0.93
     surpassing
    0.91
    迫力
    0.91
    纥
    0.90
    やっぱり
    0.90
    アンティーク
    0.89
    作った
    0.87
    Activations Density 0.512%

    No Known Activations