Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 11690
    Prev
    Next
    INDEX
    Explanations

    Google reviews and ratings

    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_31_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
     dorm
    0.42
    쁩
    0.40
     )))
    0.39
    😎
    0.38
    앗
    0.38
    ))))
    0.38
    )+'
    0.38
    습니까
    0.37
    itió
    0.37
    뽀
    0.37
    POSITIVE LOGITS
    akumar
    0.47
    複合
    0.46
     graphene
    0.43
     Haemat
    0.43
     sejumlah
    0.42
    ontinuous
    0.40
     ವಿವಿಧ
    0.40
     Akademie
    0.40
    нами
    0.39
    rens
    0.39
    Activations Density 0.009%

    No Known Activations