© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 34918
    Prev
    Next
    INDEX
    Explanations

    describing past states

    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
     now
    -1.45
    これまで
    -1.30
     since
    -1.30
    今まで
    -1.29
     eventually
    -1.28
     ahora
    -1.27
    現在は
    -1.27
     actualmente
    -1.23
     obecnie
    -1.22
     теперь
    -1.19
    POSITIVE LOGITS
     still
    2.47
    まだ
    2.41
     jeszcze
    2.27
     noch
    2.22
    still
    1.99
     ještě
    1.95
     ainda
    1.95
     هنوز
    1.92
     vielä
    1.92
     еще
    1.92
    Activations Density 0.087%

    No Known Activations