© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 190164
    Prev
    Next
    INDEX
    Explanations

    years and minutes

    np_acts-logits-general · gemini-2.5-flash-lite

    demilitarization, demographic, decline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     selectable
    0.26
     executable
    0.25
     toggle
    0.25
     damped
    0.25
     rosin
    0.24
     manually
    0.24
     inset
    0.24
    X
    0.24
     file
    0.23
     Gradient
    0.23
    POSITIVE LOGITS
     politiques
    0.32
     prostit
    0.31
     politics
    0.31
     indign
    0.30
     gobiernos
    0.29
     injustices
    0.29
     bourgeoisie
    0.29
    politics
    0.29
     parochial
    0.29
     peasantry
    0.28
    Activations Density 0.066%

    No Known Activations