© 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. 99318
    Prev
    Next
    INDEX
    Explanations

    words starting with l

    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
    ̿
    -0.83
     slight
    -0.79
     determined
    -0.79
     Ingenie
    -0.78
    ‌پدی
    -0.78
     Pferd
    -0.77
     difficulties
    -0.76
    懸
    -0.75
     اکس
    -0.75
     índices
    -0.75
    POSITIVE LOGITS
     LM
    1.30
     LU
    1.22
     LX
    1.11
     LY
    1.08
     LC
    1.07
     LO
    1.04
     LW
    1.04
     LCS
    1.00
     LH
    1.00
     LI
    0.97
    Activations Density 1.837%

    No Known Activations