© 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. 31-GEMMASCOPE-2-RES-65K
    7. 20345
    Prev
    Next
    INDEX
    Explanations

    various languages

    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_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
     ου
    0.45
     (**
    0.44
     (\$
    0.43
     刘
    0.43
     Л
    0.42
     Ern
    0.42
     (?,
    0.42
     envoy
    0.41
    爀
    0.41
    un
    0.41
    POSITIVE LOGITS
    血管
    0.41
     বিল্ডিং
    0.39
    版本的
    0.39
     nécessairement
    0.39
    녕하십니까
    0.38
    член
    0.38
    twitter
    0.37
    墻
    0.37
     دیوار
    0.37
     ilma
    0.37
    Activations Density 0.004%

    No Known Activations