© 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. 129154
    Prev
    Next
    INDEX
    Explanations

    translation id, Shop owner, Blood rhe, Dell pins

    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
     Obviously
    -1.16
    」　
    -1.13
     doesnt
    -1.09
     one
    -1.07
    同様
    -1.06
     beauté
    -1.05
     turun
    -1.05
     might
    -1.03
     empat
    -1.02
    长安
    -1.02
    POSITIVE LOGITS
    蛲
    1.16
     fleas
    1.13
     largely
    1.12
     fiabilidad
    1.12
     zejména
    1.10
    hairs
    1.09
    hirts
    1.09
     quadrado
    1.07
    уза
    1.07
     سنة
    1.06
    Activations Density 0.000%

    No Known Activations