© 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. 128639
    Prev
    Next
    INDEX
    Explanations

    replacing text or values

    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
    +:+
    -1.08
    胄
    -1.05
    ッド
    -0.99
    жал
    -0.99
     estadia
    -0.95
     perfumes
    -0.91
     for
    -0.88
     säkert
    -0.88
     partner
    -0.88
    Spoljašnje
    -0.88
    POSITIVE LOGITS
     replacements
    1.52
     Replace
    1.49
     replacement
    1.48
    replace
    1.48
    替换
    1.46
     replace
    1.40
     replacing
    1.36
     substitution
    1.30
     SUBST
    1.29
     wherever
    1.24
    Activations Density 0.057%

    No Known Activations