© 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. 18220
    Prev
    Next
    INDEX
    Explanations

    special characters followed by numbers

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

    0 followed by 1

    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
    った
    0.47
     dihasil
    0.46
     ಯಾವುದೇ
    0.45
    nicheskij
    0.44
     obtenido
    0.44
    Après
    0.43
     صہی
    0.41
    夢
    0.41
     automatiquement
    0.41
    нора
    0.41
    POSITIVE LOGITS
     Brief
    0.46
    ismo
    0.46
    昀
    0.44
    ens
    0.44
    alk
    0.44
     when
    0.44
    uyền
    0.43
     Replication
    0.43
     Redistribution
    0.42
     bandas
    0.42
    Activations Density 0.003%

    No Known Activations