© 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. 10-GEMMASCOPE-RES-131K
    7. 39690
    Prev
    Next
    INDEX
    Explanations

    people's names

    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_10/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
     impulsar
    -1.60
     JOSÉ
    -1.60
     gastronomía
    -1.52
    ṝ
    -1.49
    訁
    -1.47
    うさぎ
    -1.45
     favorecer
    -1.45
    がこの
    -1.45
     negócios
    -1.44
     hır
    -1.44
    POSITIVE LOGITS
     with
    1.66
     problems
    1.38
     used
    1.38
     Really
    1.36
     people
    1.36
     or
    1.35
     without
    1.30
     sparked
    1.29
     frequently
    1.28
     commonly
    1.28
    Activations Density 0.189%

    No Known Activations