© 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. 59404
    Prev
    Next
    INDEX
    Explanations

    Objective-C method declarations

    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
     ถูก
    -1.09
     ส่ง
    -0.96
     kedi
    -0.95
    格外
    -0.94
     ܐ
    -0.93
    vskip
    -0.93
     ใส่
    -0.91
     kalem
    -0.91
     Senin
    -0.91
    Ꮀ
    -0.90
    POSITIVE LOGITS
    void
    2.08
     void
    1.90
    a
    1.10
    id
    1.04
     voids
    1.02
    A
    1.02
     will
    1.01
    one
    0.98
    instancetype
    0.98
     губ
    0.96
    Activations Density 0.006%

    No Known Activations