© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11400
    Prev
    Next
    INDEX
    Explanations

    humanity and other abstract concepts

    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_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
    െന്നാണ്
    0.52
     süre
    0.50
    櫛
    0.49
     mettent
    0.49
    cę
    0.48
     músculos
    0.47
    isOnTimer
    0.47
    <0x9A>
    0.47
    getCharAt
    0.47
     হস্তে
    0.47
    POSITIVE LOGITS
     colonialism
    0.50
     Justice
    0.44
    class
    0.43
    producer
    0.43
    flin
    0.43
     Humanity
    0.42
     humanity
    0.41
    uman
    0.41
     sanitation
    0.39
    const
    0.39
    Activations Density 0.001%

    No Known Activations