© 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. 99650
    Prev
    Next
    INDEX
    Explanations

    domain names

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

    humanity, society, and liking

    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
    ма
    0.48
    डे
    0.47
     poisoned
    0.46
    다
    0.45
    ండి
    0.44
    ва
    0.43
    рія
    0.43
    ూ
    0.43
    ინი
    0.42
     Pupil
    0.42
    POSITIVE LOGITS
    ovou
    0.56
     utilisons
    0.56
     utilisent
    0.53
     plufieurs
    0.51
     école
    0.51
    藜
    0.50
    នៃ
    0.49
     ombil
    0.49
    ของการ
    0.49
    tomorrow
    0.49
    Activations Density 0.001%

    No Known Activations