© 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. 12705
    Prev
    Next
    INDEX
    Explanations

    various terms

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

    base64 encode and decode

    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
     Nach
    0.48
     Haiti
    0.48
     respectfully
    0.48
    ếu
    0.47
    ate
    0.47
     吃
    0.47
     tâ
    0.46
     Trinidad
    0.46
     WTO
    0.45
    curité
    0.45
    POSITIVE LOGITS
    頜
    0.48
     kinases
    0.47
    rda
    0.47
    車
    0.47
    公園
    0.47
    เช
    0.46
    正規
    0.45
    Kan
    0.45
    らしい
    0.45
    春
    0.44
    Activations Density 0.000%

    No Known Activations