© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9191
    Prev
    Next
    INDEX
    Explanations

    if you conditionally

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

    if applicable

    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_40_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
     either
    0.48
     entweder
    0.47
    either
    0.47
     ANYTHING
    0.43
    Either
    0.42
    ぺ
    0.41
    CRUD
    0.40
     attempts
    0.39
     আজকে
    0.38
     voters
    0.38
    POSITIVE LOGITS
    嫌
    0.51
    着急
    0.47
    心配
    0.47
     using
    0.46
     가능하다
    0.45
     unavoidable
    0.44
    多人
    0.44
     reusing
    0.44
     ngại
    0.44
     insistent
    0.43
    Activations Density 0.248%

    No Known Activations