© 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. 105985
    Prev
    Next
    INDEX
    Explanations

    foreign or special characters

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

    cover, over, treatment

    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
     bundling
    0.51
    m
    0.47
    REACT
    0.46
     berfungsi
    0.45
     GHz
    0.45
    delivery
    0.44
    мум
    0.44
     ICP
    0.43
    จะมี
    0.43
     dennoch
    0.43
    POSITIVE LOGITS
     گئے۔
    0.48
    ת
    0.47
    낯
    0.44
    ارا
    0.44
    㿝
    0.43
    ティング
    0.43
    临时
    0.42
    etés
    0.42
     अज्ञात
    0.41
    苔
    0.41
    Activations Density 0.001%

    No Known Activations