© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84112
    Prev
    Next
    INDEX
    Explanations

    ending with 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
     beliebtesten
    -0.98
     había
    -0.97
    днако
    -0.94
     senaste
    -0.92
    zać
    -0.92
    ക
    -0.89
    一些
    -0.86
    Składniki
    -0.85
    大部分
    -0.84
     however
    -0.82
    POSITIVE LOGITS
    supposed
    1.05
    newly
    0.99
    yearly
    0.90
    certainly
    0.90
    correctly
    0.90
    Identified
    0.89
    toward
    0.89
    cended
    0.88
    achieved
    0.88
    following
    0.88
    Activations Density 0.041%

    No Known Activations