© 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. 55391
    Prev
    Next
    INDEX
    Explanations

    cancel order

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

    broken but, slot ]

    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
    方法
    0.52
    存在
    0.44
     in
    0.44
    物は
    0.43
     pulsed
    0.43
    ことは
    0.42
    そもそも
    0.42
    も
    0.42
     TAG
    0.42
     quay
    0.42
    POSITIVE LOGITS
     énorm
    0.51
     економі
    0.50
     οικονομ
    0.48
     경기
    0.46
    ágot
    0.46
     деб
    0.46
     privacidade
    0.46
    ceed
    0.46
    다면
    0.45
     경제
    0.45
    Activations Density 0.000%

    No Known Activations