© 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. 91705
    Prev
    Next
    INDEX
    Explanations

    replace or substitute

    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
     both
    -1.05
     sekä
    -0.96
    nault
    -0.93
     together
    -0.89
     além
    -0.88
    ⟺
    -0.86
     neither
    -0.84
    問合せ
    -0.81
     BOTH
    -0.81
    rijven
    -0.80
    POSITIVE LOGITS
     by
    2.69
     with
    2.14
     vervangen
    1.38
    ด้วย
    1.32
     replaced
    1.32
    替换
    1.24
     Replaced
    1.17
     bằng
    1.15
    replaced
    1.09
     REPLACE
    1.08
    Activations Density 0.042%

    No Known Activations