© 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. 65329
    Prev
    Next
    INDEX
    Explanations

    specific placement choice

    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
     parfü
    -1.12
     essentielle
    -1.11
     kere
    -1.10
     tö
    -1.09
     rü
    -1.06
    РАЗ
    -1.05
     romantis
    -1.05
     beni
    -1.04
    kapat
    -1.04
     vek
    -1.03
    POSITIVE LOGITS
     chosen
    1.59
     choice
    1.32
     choices
    1.23
     placement
    1.19
     scelta
    1.10
    chosen
    1.06
     escolh
    1.06
     arrangement
    1.06
     position
    1.03
     선택
    1.00
    Activations Density 0.120%

    No Known Activations