© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 14173
    Prev
    Next
    INDEX
    Explanations

    speaking of

    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_40_width_262k_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
     talked
    0.57
    talk
    0.56
     talk
    0.55
    Talk
    0.50
     talks
    0.48
     Talk
    0.48
    谈
    0.44
    nv
    0.44
    ativas
    0.43
    ंटे
    0.41
    POSITIVE LOGITS
     tube
    0.42
     ignition
    0.41
     volumes
    0.39
     Algorithms
    0.38
    founded
    0.38
     Tube
    0.37
     Methoden
    0.37
     contraindicated
    0.37
     Founded
    0.37
     method
    0.37
    Activations Density 0.005%

    No Known Activations