© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99152
    Prev
    Next
    INDEX
    Explanations

    copyright and licensing

    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
     raza
    -0.89
    €”
    -0.85
     espet
    -0.83
     mikä
    -0.79
    ↫
    -0.79
     perche
    -0.77
    нятно
    -0.77
    粝
    -0.76
     phénom
    -0.75
     canta
    -0.75
    POSITIVE LOGITS
     напряжения
    0.90
    Počet
    0.83
     instead
    0.82
     Kette
    0.77
     ["",
    0.75
    介
    0.75
    geste
    0.74
     Kome
    0.73
    に戻
    0.73
     αγα
    0.72
    Activations Density 0.000%

    No Known Activations