© 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. 26374
    Prev
    Next
    INDEX
    Explanations

    about or as certain topics

    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
    औ
    -1.18
     هنگ
    -1.02
    azienda
    -1.01
    seamnă
    -1.00
     heerlijk
    -0.99
     usus
    -0.99
     zacht
    -0.99
    Œ
    -0.99
    eload
    -0.97
     zijne
    -0.97
    POSITIVE LOGITS
    p
    1.17
     question
    1.17
    part
    1.12
     links
    1.12
     pregunta
    1.11
     issue
    1.09
     questions
    1.04
    vertrag
    1.03
    out
    1.02
     timing
    1.02
    Activations Density 0.015%

    No Known Activations