© 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. 29787
    Prev
    Next
    INDEX
    Explanations

    location descriptions and associated nouns

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

    color restoration

    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
    ﻁ
    0.40
    ;
    0.39
     revital
    0.38
     overhauled
    0.37
     sports
    0.37
     اولى
    0.36
     ansch
    0.36
    ﻅ
    0.36
    ላቸው
    0.36
    センス
    0.36
    POSITIVE LOGITS
     będ
    0.47
     보내
    0.45
    ları
    0.45
     언급
    0.44
    larını
    0.44
     Insights
    0.44
     ऑफलाइन
    0.44
    ใน
    0.43
     Jabal
    0.43
     آخرین
    0.43
    Activations Density 0.000%

    No Known Activations