© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14179
    Prev
    Next
    INDEX
    Explanations

    offering to help or start an action

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

    let's wrap, let's, see, shall

    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_16k_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
     autrefois
    0.46
     érde
    0.45
     beeindruck
    0.45
     kenapa
    0.43
     Nej
    0.42
     Ukraj
    0.42
     ternyata
    0.41
     결국
    0.41
     unlike
    0.41
     اغلب
    0.41
    POSITIVE LOGITS
    看看
    0.59
    看一下
    0.58
    我們先
    0.56
    ましょう
    0.55
    來看一下
    0.54
    先把
    0.54
     давайте
    0.54
     এখনই
    0.54
    吧
    0.54
     볼게요
    0.52
    Activations Density 0.142%

    No Known Activations