© 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. 34200
    Prev
    Next
    INDEX
    Explanations

    designers, mice, cleaners, disease

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

    describes how things are

    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
     therefrom
    0.48
    훨
    0.43
     semelhante
    0.43
     آنان
    0.38
    更能
    0.38
    其
    0.38
    輻
    0.38
    ඒ
    0.37
     therewith
    0.36
     reduzir
    0.36
    POSITIVE LOGITS
    既然
    0.47
     প্রথমেই
    0.45
     যেহেতু
    0.44
     একেবারে
    0.43
     অধিকাংশ
    0.42
     বেশিরভাগ
    0.41
    oretically
    0.38
     hầu
    0.38
     গেলেও
    0.38
    有個
    0.38
    Activations Density 0.074%

    No Known Activations