© 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. 31-GEMMASCOPE-2-RES-262K
    7. 1998
    Prev
    Next
    INDEX
    Explanations

    non-english characters

    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_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
                                   
    0.58
     berücksichtigt
    0.53
    についても
    0.51
     ……………………
    0.50
    ட்டிக்க
    0.47
       
    0.47
     prawidł
    0.47
    bezpie
    0.46
    ----------------
    0.45
    ㅋㅋㅋㅋㅋㅋㅋㅋ
    0.45
    POSITIVE LOGITS
     അദ്ദേ
    0.65
     socalled
    0.63
     wellknown
    0.59
    ナトリ
    0.51
     $%
    0.50
    нача
    0.49
    混凝
    0.49
     עד
    0.48
     או
    0.47
    ія
    0.45
    Activations Density 0.153%

    No Known Activations