© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35759
    Prev
    Next
    INDEX
    Explanations

    method calls and statements

    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
     was
    -1.44
     for
    -1.42
     At
    -1.24
     By
    -1.21
     are
    -1.16
     So
    -1.09
     No
    -1.07
     zur
    -1.06
    への
    -1.05
     most
    -1.04
    POSITIVE LOGITS
    Давайте
    1.48
     '*',
    1.34
    僕が
    1.31
    槼
    1.26
    1.26
     EEUU
    1.20
     Licenses
    1.19
     '.',
    1.18
     tamaños
    1.16
     Presiden
    1.15
    Activations Density 0.001%

    No Known Activations