© 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. 218702
    Prev
    Next
    INDEX
    Explanations

    wind yesterday and reaching

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

    multilingual information processing

    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
    uited
    0.46
    ळी
    0.42
    meshes
    0.41
    nels
    0.40
    苚
    0.40
    toluene
    0.40
    tolyl
    0.40
    Extension
    0.39
    Funding
    0.39
    ρίες
    0.39
    POSITIVE LOGITS
     Cuenta
    0.56
     Truman
    0.50
     Г
    0.50
     קי
    0.49
     Ц
    0.48
     圖
    0.47
    िंग
    0.47
     จด
    0.47
     말씀을
    0.46
     Филип
    0.46
    Activations Density 0.000%

    No Known Activations