© 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. 66153
    Prev
    Next
    INDEX
    Explanations

    problem, any, or satisfied

    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
    مقدمه
    -1.24
     搞笑
    -1.20
     sorprendió
    -1.20
     efekt
    -1.17
     pareció
    -1.16
     Entfer
    -1.12
     suéter
    -1.09
     olvido
    -1.09
    nende
    -1.08
     capuz
    -1.08
    POSITIVE LOGITS
     or
    2.25
     или
    1.17
     regarding
    1.10
     during
    1.09
     after
    1.07
    ieważ
    1.07
     your
    1.05
     årets
    1.05
    comp
    1.00
     with
    0.97
    Activations Density 0.002%

    No Known Activations