© 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. 22-GEMMASCOPE-RES-131K
    7. 72433
    Prev
    Next
    INDEX
    Explanations

    code constructs and 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_22/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
     Consultez
    -0.90
     early
    -0.90
     daarvoor
    -0.88
     iedereen
    -0.85
    Función
    -0.84
     reveló
    -0.82
    しますが
    -0.82
    Khach
    -0.81
     meet
    -0.80
    첫
    -0.80
    POSITIVE LOGITS
     newcomers
    0.93
    (||
    0.88
     punta
    0.88
    ensores
    0.85
    下来的
    0.84
    рій
    0.83
    いくら
    0.82
     forbearance
    0.82
     растения
    0.82
    sizeof
    0.82
    Activations Density 0.002%

    No Known Activations