© 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. 225193
    Prev
    Next
    INDEX
    Explanations

    areas, terrain, aircraft, remote areas

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

    influences how things are described

    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
    ategory
    0.41
     ÷
    0.40
    LetterGrade
    0.39
     -&
    0.39
     vuoden
    0.38
     BECAUSE
    0.38
    wisdom
    0.38
     Vì
    0.37
     &'
    0.37
     =",
    0.37
    POSITIVE LOGITS
    ﻓ
    0.48
    ここ
    0.48
     местности
    0.46
    周囲
    0.45
     इलाकों
    0.45
     బయ
    0.45
     grasslands
    0.45
     инженер
    0.45
    杆
    0.44
    地形
    0.44
    Activations Density 0.002%

    No Known Activations