© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 51766
    Prev
    Next
    INDEX
    Explanations

    web links

    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_65k_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
    ］
    0.44
    ॉइड
    0.40
     คิด
    0.38
    стройство
    0.38
    Renderer
    0.38
     Когда
    0.38
     बिल्डिंग
    0.38
    孔
    0.38
    ަކ
    0.37
    ется
    0.36
    POSITIVE LOGITS
    å
    0.47
    ່ວນ
    0.46
     are
    0.46
    ystems
    0.43
     são
    0.41
    peicher
    0.41
     PlayStation
    0.41
    ports
    0.40
    ğ
    0.39
     linéaires
    0.38
    Activations Density 0.014%

    No Known Activations