© 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. 26535
    Prev
    Next
    INDEX
    Explanations

    replacement or substitution

    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
     mejorar
    -0.94
     participaron
    -0.88
    娛
    -0.87
    essoal
    -0.84
     each
    -0.82
    Betyg
    -0.81
    Ohhhh
    -0.80
    Ⓗ
    -0.79
    Ohhh
    -0.78
    Ooooo
    -0.78
    POSITIVE LOGITS
     instead
    1.48
    代替
    1.40
     replacements
    1.33
     replacement
    1.24
    replace
    1.21
     zamiast
    1.21
     replacing
    1.20
     substitute
    1.19
    替代
    1.19
     replace
    1.17
    Activations Density 0.061%

    No Known Activations