© 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. 61726
    Prev
    Next
    INDEX
    Explanations

    postal thefts and letters

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

    stereotype itself

    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
    euro
    0.39
    annya
    0.38
    urile
    0.38
    ure
    0.38
    file
    0.38
    ઢ
    0.37
    router
    0.37
    ierra
    0.37
    ova
    0.37
    ವಾದ
    0.37
    POSITIVE LOGITS
     zweimal
    0.55
     étudiant
    0.52
     macrophage
    0.51
     Μα
    0.49
     आईआईटी
    0.49
    மும்
    0.46
     조사
    0.45
    🐋
    0.45
     Spannung
    0.44
     втором
    0.44
    Activations Density 0.000%

    No Known Activations