© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9833
    Prev
    Next
    INDEX
    Explanations

    google

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Google
    0.43
    UDE
    0.43
    global
    0.42
     بہانہ
    0.40
    iau
    0.39
    ிகளை
    0.39
    언
    0.38
    แหน
    0.38
     റ
    0.38
    ಂಗಳ
    0.38
    POSITIVE LOGITS
     thu
    0.43
     fibra
    0.40
    王国
    0.40
     万元
    0.39
     Gew
    0.39
     Mih
    0.39
     تعالى
    0.39
     Play
    0.39
     характеристи
    0.38
    ர்ந்து
    0.38
    Activations Density 0.049%

    No Known Activations