© 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. 129428
    Prev
    Next
    INDEX
    Explanations

    cookies and licenses

    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
     calzado
    -1.43
     från
    -1.40
    gunakan
    -1.38
    ),
    -1.35
    書の
    -1.32
     bricolaje
    -1.31
     estreno
    -1.30
     läs
    -1.30
     zapato
    -1.30
    (){
    -1.29
    POSITIVE LOGITS
     compatri
    1.33
     and
    1.10
     playboy
    1.07
     assassins
    1.07
     Grüßen
    1.05
     infernal
    1.03
     corpi
    1.02
     confr
    1.01
    Vinc
    0.99
     Karang
    0.98
    Activations Density 0.267%

    No Known Activations