© 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. 237654
    Prev
    Next
    INDEX
    Explanations

    life in, measured temperature, feature film

    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
    いずれ
    0.50
    该
    0.47
    本
    0.47
    庸
    0.47
    ﻨ
    0.45
    天井
    0.45
    随后
    0.44
    条
    0.44
    タイミング
    0.44
    왈
    0.44
    POSITIVE LOGITS
    rakash
    0.50
    ãos
    0.50
    ông
    0.49
    ão
    0.47
    ôtels
    0.47
     पोर्टल
    0.46
     বিস্ফ
    0.46
     membeli
    0.46
     Renata
    0.45
    hö
    0.45
    Activations Density 0.001%

    No Known Activations