© 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. 163173
    Prev
    Next
    INDEX
    Explanations

    conditional and causal language

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

    dangerous synthesis

    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
     extérieure
    0.48
     intérieure
    0.48
     HomeController
    0.47
     LOCATION
    0.47
    ൨
    0.46
     Microphone
    0.46
    🤳
    0.46
     //=>
    0.45
     Outlet
    0.45
     নিচের
    0.45
    POSITIVE LOGITS
     libro
    0.44
     registr
    0.44
     enige
    0.43
     dyslexia
    0.42
     doar
    0.41
    registr
    0.41
     cex
    0.41
     reiniciar
    0.41
    et
    0.41
    cex
    0.40
    Activations Density 0.002%

    No Known Activations