© 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. 68274
    Prev
    Next
    INDEX
    Explanations

    distinction between groups

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

    removing invasive species

    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
     மில்லியன்
    0.54
     அவரது
    0.51
     উদ
    0.48
    目標
    0.48
     प्रस्तावित
    0.48
    новой
    0.47
    新たな
    0.47
    К
    0.46
    MACH
    0.46
    рт
    0.45
    POSITIVE LOGITS
     logged
    0.41
     aberr
    0.41
     ilość
    0.41
     degeneracy
    0.40
     vraie
    0.39
     शही
    0.39
    ={
    0.39
     authoritarian
    0.39
     patriarchal
    0.39
     sucks
    0.39
    Activations Density 0.000%

    No Known Activations