© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 256
    Prev
    Next
    INDEX
    Explanations

    input.int or public Key

    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
     concurred
    0.39
     Phal
    0.39
    ⇵
    0.38
    促进
    0.37
     scalable
    0.36
     hotter
    0.35
     июня
    0.35
     Infos
    0.35
     জাহান
    0.35
     pendiente
    0.35
    POSITIVE LOGITS
    Chap
    0.34
    Trump
    0.34
    NAP
    0.32
     NAP
    0.31
    harm
    0.31
    解釋
    0.31
    Lith
    0.30
    ﭔ
    0.30
    irm
    0.29
    irmi
    0.29
    Activations Density 0.002%

    No Known Activations