© 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. 186153
    Prev
    Next
    INDEX
    Explanations

    access and planning

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

    understanding phenomena

    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
     junkie
    0.56
    et
    0.53
    oliko
    0.53
     Oliver
    0.52
     Concepts
    0.52
    oló
    0.52
     subtiliter
    0.52
     石
    0.52
     रणबीर
    0.51
     narrower
    0.50
    POSITIVE LOGITS
    Ba
    0.47
    創建
    0.46
    create
    0.45
    Q
    0.45
    Β
    0.44
    ﻤ
    0.44
    ﺴ
    0.44
    扶
    0.43
    ︎
    0.42
    鎖
    0.42
    Activations Density 0.001%

    No Known Activations