© 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. 157171
    Prev
    Next
    INDEX
    Explanations

    furniture brands and retailers

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

    live against viruses

    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
    ことから
    0.50
    ດ້ວຍ
    0.50
    㐄
    0.49
    gateTime
    0.49
    生产者
    0.48
    vertine
    0.47
    尽可能
    0.46
     Sall
    0.46
    տն
    0.46
     insurmountable
    0.45
    POSITIVE LOGITS
    ขาย
    0.53
    lemb
    0.48
     dipakai
    0.48
     enzim
    0.47
    TY
    0.46
    タン
    0.46
     lembaga
    0.46
    َی
    0.46
    j
    0.45
    Enviar
    0.44
    Activations Density 0.001%

    No Known Activations