© 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. 137151
    Prev
    Next
    INDEX
    Explanations

    invite to attend

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

    pandemic or leaving

    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
    u
    0.51
    if
    0.51
     DTC
    0.47
     ,
    0.46
    AVC
    0.46
    compatibility
    0.45
    "],
    0.44
    p
    0.44
     AA
    0.44
    op
    0.44
    POSITIVE LOGITS
    䂝
    0.47
     toán
    0.46
     இதில்
    0.46
    乱流
    0.46
    ěn
    0.45
    耘
    0.44
    rieben
    0.44
    enl
    0.43
    ãos
    0.43
     बाई
    0.43
    Activations Density 0.002%

    No Known Activations