© 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. 33432
    Prev
    Next
    INDEX
    Explanations

    in or at a location

    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
    верь
    -1.27
    は
    -1.20
     ибо
    -1.12
    による
    -1.12
    brada
    -1.10
    其
    -1.05
     زیرا
    -1.05
    はこの
    -1.04
    ienė
    -1.04
     يساعد
    -1.03
    POSITIVE LOGITS
    に行って
    1.62
     you
    1.59
     I
    1.55
    に行った
    1.43
     that
    1.43
     people
    1.40
     it
    1.34
    だったり
    1.30
    なんですよ
    1.28
     they
    1.26
    Activations Density 0.006%

    No Known Activations