© 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. 109847
    Prev
    Next
    INDEX
    Explanations

    prefix completion

    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
     появится
    -1.16
    訁
    -1.13
     miseries
    -1.01
     breathtaking
    -0.97
     attendant
    -0.95
     aufnehmen
    -0.95
     mitos
    -0.95
     мона
    -0.94
    罰
    -0.94
    未能
    -0.93
    POSITIVE LOGITS
    利率
    1.01
    の中でも
    0.99
    一般的
    0.98
    為に
    0.98
    kapital
    0.97
    modb
    0.97
    ᯅ
    0.94
    скажите
    0.94
     interessant
    0.93
     схо
    0.91
    Activations Density 0.077%

    No Known Activations