© 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. 73087
    Prev
    Next
    INDEX
    Explanations

    new and existing contexts

    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
     botões
    -1.17
     prévoir
    -1.16
    mainly
    -1.16
    捱
    -1.14
     anpassen
    -1.14
     предыду
    -1.14
    toxicity
    -1.13
     .........
    -1.13
     soprattutto
    -1.12
     again
    -1.10
    POSITIVE LOGITS
     febru
    1.36
     Generally
    1.19
     meleg
    1.17
    határoz
    1.16
    Él
    1.16
     Meksika
    1.16
     Although
    1.15
    mentes
    1.15
     When
    1.14
     ngào
    1.14
    Activations Density 0.036%

    No Known Activations