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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 15829
    Prev
    Next
    INDEX
    Explanations

    maven artifact deployment and repositories

    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_262k_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
    啱
    0.44
     zusätzlichen
    0.39
     přid
    0.38
     रत
    0.38
     subito
    0.38
    ])$
    0.37
    sourceFolder
    0.36
     بالنسبة
    0.36
     absences
    0.36
     fillColorSpace
    0.36
    POSITIVE LOGITS
     Iran
    0.46
     метал
    0.45
     Persia
    0.42
    Iran
    0.42
     ईरान
    0.42
     Plex
    0.41
     Tehran
    0.41
     импе
    0.41
    metal
    0.40
    倫
    0.39
    Activations Density 0.003%

    No Known Activations