© 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. 107822
    Prev
    Next
    INDEX
    Explanations

    is now / are now

    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
     também
    -1.47
     tampoco
    -1.45
     también
    -1.42
    也
    -1.32
     даже
    -1.30
    either
    -1.30
    still
    -1.30
    also
    -1.25
    也是
    -1.21
    even
    -1.20
    POSITIVE LOGITS
     retourne
    0.95
    頃に
    0.95
     anfitrión
    0.94
     fonctionnent
    0.92
    够了
    0.89
    えました
    0.88
    どれだけ
    0.87
    angkutan
    0.85
     contiennent
    0.85
     καθώς
    0.85
    Activations Density 0.090%

    No Known Activations