© 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. 165616
    Prev
    Next
    INDEX
    Explanations

    account until

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

    sun emits slightly less

    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
    关节
    0.50
    单
    0.48
    ม
    0.47
     juridique
    0.47
    ці
    0.45
    品种
    0.45
    环
    0.45
     jurídico
    0.44
    Ὀ
    0.44
    债券
    0.44
    POSITIVE LOGITS
    stances
    0.47
    seca
    0.46
     Nesse
    0.44
    income
    0.43
    ancient
    0.42
    mentioned
    0.42
    sores
    0.42
    lu
    0.41
    otransfer
    0.41
    lema
    0.41
    Activations Density 0.002%

    No Known Activations