© 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. 184153
    Prev
    Next
    INDEX
    Explanations

    usually for

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

    Google Translate, analyzing, finance, Difficulty

    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
    勰
    0.52
    炤
    0.51
    如图
    0.47
    这条
    0.47
    如下
    0.47
    知道
    0.47
    射线
    0.45
    该
    0.45
     والب
    0.44
    这本书
    0.44
    POSITIVE LOGITS
     kalian
    0.52
     นิด
    0.48
     ११
    0.47
     meines
    0.47
     confessions
    0.46
     satir
    0.46
    ülmesi
    0.46
     মূল্যা
    0.46
     nomes
    0.46
     podemos
    0.46
    Activations Density 0.001%

    No Known Activations