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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106773
    Prev
    Next
    INDEX
    Explanations

    this.property access

    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
     same
    -0.91
     as
    -0.88
    ärä
    -0.86
    サイクル
    -0.86
    とおり
    -0.85
     eager
    -0.84
     amidst
    -0.84
    と思われます
    -0.82
    周泽楷
    -0.81
     over
    -0.80
    POSITIVE LOGITS
    options
    1.09
    Rozm
    1.00
     زيادة
    0.91
     mangá
    0.91
    Итог
    0.90
    Ặ
    0.89
    ـــ
    0.89
     Options
    0.88
     leitor
    0.84
    aporan
    0.84
    Activations Density 0.012%

    No Known Activations