© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1376
    Prev
    Next
    INDEX
    Explanations

    hi and hey greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    ’;
    0.86
    ’:
    0.83
     $$\
    0.82
     करीत
    0.81
     bitmap
    0.81
     \[
    0.80
     spurious
    0.78
     extol
    0.77
     참조
    0.76
    こうした
    0.76
    POSITIVE LOGITS
     Zayn
    1.20
     Jungkook
    1.20
     Taehyung
    1.13
    😫
    1.08
    𒊹
    1.06
    😑
    1.04
    💭
    1.04
    😒
    1.04
    🖕
    1.02
    🕸
    1.01
    Activations Density 0.089%

    No Known Activations