© 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. 34-GEMMASCOPE-RES-131K
    7. 118398
    Prev
    Next
    INDEX
    Explanations

    versus, vs

    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
     Polisi
    -1.10
     Dopo
    -1.09
    Răsp
    -1.08
    になったら
    -1.07
     sadar
    -1.05
    ICATED
    -1.04
     deras
    -1.02
     Люди
    -1.01
     mici
    -0.98
     katk
    -0.98
    POSITIVE LOGITS
     Role
    1.65
     Versus
    1.54
     vs
    1.35
     Uses
    1.28
     versus
    1.25
    Role
    1.21
     Case
    1.20
    %;
    1.19
     Different
    1.18
     Definition
    1.18
    Activations Density 0.466%

    No Known Activations