© 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. 188349
    Prev
    Next
    INDEX
    Explanations

    after starting or installing

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

    innovation and speed

    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
    便利
    0.52
    大阪
    0.51
    侧
    0.50
    澳
    0.50
    以
    0.49
    鱷
    0.49
    电子
    0.48
    一起
    0.47
    行列
    0.47
    下载
    0.47
    POSITIVE LOGITS
    swadian
    0.49
    punctuation
    0.48
    anath
    0.46
     мати
    0.46
    वारीत
    0.46
    apayati
    0.46
    amata
    0.46
     น
    0.45
     palav
    0.45
    abhave
    0.45
    Activations Density 0.001%

    No Known Activations