© 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. 42512
    Prev
    Next
    INDEX
    Explanations

    mosaic sculptures and community structures

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

    completed urgent tasks

    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
     じゃ
    0.54
     yearly
    0.50
     cuantit
    0.47
     jähr
    0.46
     später
    0.46
     привод
    0.44
     sinnvoll
    0.43
     量
    0.43
     مقدار
    0.42
     میزان
    0.42
    POSITIVE LOGITS
    𝟑
    0.47
     Nation
    0.44
    лната
    0.44
    ﻖ
    0.43
    सागर
    0.43
    ссив
    0.42
     Chatt
    0.42
    퐫
    0.42
    氳
    0.42
    Му
    0.42
    Activations Density 0.000%

    No Known Activations