© 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. 186482
    Prev
    Next
    INDEX
    Explanations

    accelerate debt, client financial, Carl therapist, coarsely charred skins, stone security

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

    actions and their results

    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
    зив
    0.46
     দ্বিত
    0.46
    缺少
    0.45
     שהוא
    0.45
    м
    0.45
    плуа
    0.45
    Reuse
    0.44
    tena
    0.44
    পী
    0.43
    પ
    0.43
    POSITIVE LOGITS
     Puede
    0.47
     başlayalım
    0.46
     guer
    0.45
     sizi
    0.45
     ejemplo
    0.45
     Vape
    0.45
     Mini
    0.44
     exorbit
    0.43
     guerr
    0.43
     examined
    0.43
    Activations Density 0.002%

    No Known Activations