© 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. 64438
    Prev
    Next
    INDEX
    Explanations

    growth and improvement

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

    growing demand and awareness

    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
     మనం
    0.52
    码
    0.51
    收费
    0.49
    总
    0.49
    分为
    0.48
     bây
    0.48
    酞
    0.47
    魑
    0.46
    错了
    0.46
    变成了
    0.46
    POSITIVE LOGITS
     favourable
    0.53
     improving
    0.50
     collaborated
    0.49
     improves
    0.49
     favorable
    0.48
     improve
    0.48
     verbessert
    0.47
     promotes
    0.47
     sourcing
    0.47
     einfacher
    0.46
    Activations Density 0.022%

    No Known Activations