© 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. 115946
    Prev
    Next
    INDEX
    Explanations

    IT enthusiast

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

    direct protests

    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
     दुनिया
    0.50
     Safety
    0.49
     Live
    0.48
    の世界
    0.48
     our
    0.48
     বিশ্বের
    0.48
     Since
    0.48
    )$.
    0.47
     컴퓨
    0.47
     Lives
    0.47
    POSITIVE LOGITS
    fcast
    0.47
     judiciales
    0.46
     reluctantly
    0.46
    nicht
    0.46
     frown
    0.46
    blacklist
    0.46
     revolver
    0.45
    貶
    0.45
     kellett
    0.45
     remon
    0.45
    Activations Density 0.002%

    No Known Activations