© 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. 128829
    Prev
    Next
    INDEX
    Explanations

    streak-free gifts Nit

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

    depths, Moon, dance, games, share, quick

    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
    一年
    0.48
    พ
    0.44
     আনন্দ
    0.43
    ν
    0.43
    植
    0.43
     atk
    0.42
    ქვთ
    0.42
    墓
    0.41
     wilfully
    0.41
    显示
    0.41
    POSITIVE LOGITS
    searchInput
    0.52
    ๘
    0.51
    Lieutenant
    0.49
    urlopen
    0.48
    limiting
    0.47
    Hawk
    0.46
    Tareas
    0.46
    Algorithm
    0.46
    Gan
    0.46
    FunctionName
    0.46
    Activations Density 0.001%

    No Known Activations