© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16344
    Prev
    Next
    INDEX
    Explanations

    will reach

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

    colors and positive emotions

    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_16k_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
    בית
    0.53
    ຢູ່
    0.50
     despatched
    0.49
    ضاء
    0.49
    ústria
    0.48
    ये
    0.47
    ='%
    0.47
     docente
    0.47
    ﻒ
    0.46
    cedor
    0.45
    POSITIVE LOGITS
     डेस्क
    0.47
     เหมือน
    0.45
     moods
    0.44
     GON
    0.43
     Gilead
    0.43
    အတွက်
    0.43
    IZING
    0.43
     (&
    0.42
     lâu
    0.42
     JOY
    0.42
    Activations Density 0.000%

    No Known Activations