© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10413
    Prev
    Next
    INDEX
    Explanations

    safe and helpful AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    policy
    0.55
    政策
    0.52
     yatırım
    0.44
    incott
    0.43
     policy
    0.43
    정책
    0.43
    ./
    0.42
     raining
    0.42
    rizio
    0.42
    arlama
    0.42
    POSITIVE LOGITS
    快適
    0.47
    尽可能
    0.46
     undisturbed
    0.45
     möglichst
    0.43
     integrable
    0.43
     accessibles
    0.42
     unnoticed
    0.42
    広
    0.42
     সহজে
    0.41
     accessible
    0.41
    Activations Density 0.637%

    No Known Activations