© 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. 206590
    Prev
    Next
    INDEX
    Explanations

    quality, memory, violating, trends

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

    explaining concepts and how things work

    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
    Dogs
    0.55
    ן
    0.55
    Dog
    0.51
    ザ
    0.50
    ח
    0.49
     dość
    0.49
    অন
    0.48
     মোটামুটি
    0.48
    ড়
    0.48
    не
    0.47
    POSITIVE LOGITS
     Therapeut
    0.54
    inom
    0.52
    igere
    0.51
    绎
    0.50
     Cumm
    0.50
    uelles
    0.49
     Qin
    0.48
     Invention
    0.48
    娲
    0.47
     Einwill
    0.46
    Activations Density 0.001%

    No Known Activations