© 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. 72572
    Prev
    Next
    INDEX
    Explanations

    different from others

    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
     lepší
    -1.09
     nejen
    -0.96
     not
    -0.93
     odpowied
    -0.90
    czne
    -0.86
    捱
    -0.85
    idados
    -0.84
     alongside
    -0.84
     couvercle
    -0.84
     along
    -0.83
    POSITIVE LOGITS
     because
    1.70
     porque
    1.32
     karena
    1.25
    Unlike
    1.25
    而是
    1.23
    Because
    1.22
     anymore
    1.20
     usual
    1.20
     where
    1.19
     that
    1.17
    Activations Density 0.059%

    No Known Activations