© 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. 59464
    Prev
    Next
    INDEX
    Explanations

    certain amount or condition

    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
     seleccionar
    -0.79
    長く
    -0.77
     лето
    -0.76
    Schedulers
    -0.76
    UBLE
    -0.75
    兩個
    -0.75
    GenerationType
    -0.74
    pagest
    -0.72
     饰
    -0.72
    toBeTruthy
    -0.71
    POSITIVE LOGITS
     specified
    2.67
    一定
    2.30
     опреде
    2.05
    指定
    2.05
    specified
    2.02
    Specified
    1.99
     prescribed
    1.97
     Specified
    1.93
     predetermined
    1.93
     certain
    1.88
    Activations Density 0.204%

    No Known Activations