© 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. 47765
    Prev
    Next
    INDEX
    Explanations

    the followed by a noun

    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
     headlong
    -0.92
    甦
    -0.83
    艦隊
    -0.82
     野菜
    -0.79
    ồi
    -0.78
    ຈ
    -0.78
    脇
    -0.77
     размеров
    -0.75
     hastily
    -0.75
    ẩy
    -0.74
    POSITIVE LOGITS
    beginning
    1.00
    $"
    0.96
     selben
    0.92
    __("
    0.89
     felhasznál
    0.87
     outskirts
    0.85
     entirety
    0.84
     comforts
    0.83
     confin
    0.82
     span
    0.81
    Activations Density 0.086%

    No Known Activations