© 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. 223019
    Prev
    Next
    INDEX
    Explanations

    others, reason, government, God

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

    possessive pronouns, whose, which

    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
     outperform
    0.47
     SUPPL
    0.46
     outweighed
    0.44
    較
    0.43
    Cheers
    0.43
    預
    0.42
     APPRO
    0.42
    מבר
    0.42
    ɸ
    0.42
    σια
    0.41
    POSITIVE LOGITS
     وإ
    0.51
     җиңү
    0.48
     Yal
    0.48
     waarbij
    0.47
     cuya
    0.46
     दूसरों
    0.46
     cuyo
    0.45
     Whose
    0.45
     آهنگ
    0.45
     выдви
    0.45
    Activations Density 0.000%

    No Known Activations