© 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. 224147
    Prev
    Next
    INDEX
    Explanations

    movement

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

    increase growthchange startgainexpandprofitaddednewgrowraise

    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
    イズ
    0.46
     ਅਤੇ
    0.46
     এবং
    0.45
    และ
    0.45
    ocols
    0.44
    чого
    0.43
    noons
    0.42
    и
    0.42
     Jno
    0.42
     вона
    0.42
    POSITIVE LOGITS
     indestruct
    0.50
    增
    0.46
     impuls
    0.46
     accelerate
    0.45
     lanzar
    0.45
     crecer
    0.45
     lancé
    0.45
     desliz
    0.45
     değişt
    0.44
    增长
    0.44
    Activations Density 0.000%

    No Known Activations