© 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. 225127
    Prev
    Next
    INDEX
    Explanations

    domain hosting registration

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

    complex partial seizures

    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
    厅
    0.49
    رشف
    0.47
    و
    0.47
     vál
    0.45
    菌
    0.45
     températures
    0.44
    atá
    0.43
    ر
    0.43
    জনের
    0.42
    يرا
    0.42
    POSITIVE LOGITS
    ity
    0.50
     July
    0.50
    urities
    0.49
    ama
    0.48
    adilan
    0.48
    ake
    0.48
    inth
    0.47
    unication
    0.47
     Singing
    0.46
    𐰚
    0.46
    Activations Density 0.000%

    No Known Activations