© 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. 48004
    Prev
    Next
    INDEX
    Explanations

    for and its following noun phrase

    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
    Также
    -0.97
    もあった
    -0.92
     naš
    -0.92
    でも
    -0.88
     waa
    -0.88
     apprécié
    -0.87
     tphcm
    -0.86
     extranjera
    -0.86
    日程
    -0.86
    baliknya
    -0.86
    POSITIVE LOGITS
     convenience
    1.00
    erea
    0.97
    🤯
    0.93
     razem
    0.89
    getCurrent
    0.86
    gathered
    0.86
    quent
    0.85
    rard
    0.85
    bearing
    0.85
     want
    0.84
    Activations Density 0.041%

    No Known Activations