© 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. 26088
    Prev
    Next
    INDEX
    Explanations

    remove, delete, ToRemove

    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
     Missing
    -0.83
     new
    -0.82
    homem
    -0.79
    ouverture
    -0.78
     которого
    -0.78
     better
    -0.77
     able
    -0.77
     podat
    -0.76
     Augenblick
    -0.75
    installa
    -0.75
    POSITIVE LOGITS
    ToRemove
    1.25
     remove
    1.09
     removal
    1.05
    เคย
    1.05
    anglement
    1.05
    Последние
    1.04
     kapas
    1.04
    léans
    1.02
    remove
    1.01
    ToDelete
    0.99
    Activations Density 0.034%

    No Known Activations