© 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. 132493
    Prev
    Next
    INDEX
    Explanations

    contest before

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

    font rendering and visual characteristics

    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
    ఐ
    0.47
    ផ្ល
    0.47
    𝘭
    0.47
    펍
    0.46
    版本
    0.46
    🌄
    0.46
    ⸝
    0.45
    射
    0.45
    泳
    0.44
    Чем
    0.44
    POSITIVE LOGITS
     deze
    0.51
     een
    0.50
     taboo
    0.50
     compra
    0.49
     diccionario
    0.48
     universitaire
    0.46
     enclave
    0.46
     croche
    0.45
     classique
    0.45
     mittens
    0.45
    Activations Density 0.001%

    No Known Activations