© 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. 220298
    Prev
    Next
    INDEX
    Explanations

    encoding and processing information

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

    makes it easier

    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
    聯繫
    0.48
    ﻛ
    0.46
     límites
    0.45
    亓
    0.44
     દિવસે
    0.43
     bâtiment
    0.43
    ОР
    0.43
     الصحية
    0.43
    亣
    0.43
    니아
    0.41
    POSITIVE LOGITS
     Encode
    0.53
     encoding
    0.52
     enqueue
    0.50
     Utama
    0.49
     Encoding
    0.49
     Allocation
    0.48
     Encoder
    0.48
    metik
    0.47
     Figures
    0.46
     Sakurai
    0.45
    Activations Density 0.001%

    No Known Activations