© 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. 69229
    Prev
    Next
    INDEX
    Explanations

    newcomers immigration generations cloned hunts

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

    specific words or phrases

    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
    죄
    0.51
    罪
    0.50
     incentivize
    0.48
    ਾਨ
    0.47
    ЕН
    0.47
    ੁੱ
    0.47
    ᴛ
    0.47
     આરોપી
    0.45
    在你
    0.44
    َا
    0.44
    POSITIVE LOGITS
     Rapid
    0.44
     그러나
    0.43
     vẫn
    0.43
     αλλά
    0.43
     Fl
    0.42
     egyéb
    0.42
     Combien
    0.42
     Audubon
    0.41
     newcomers
    0.41
     Oiseau
    0.41
    Activations Density 0.001%

    No Known Activations