© 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-262K
    7. 12724
    Prev
    Next
    INDEX
    Explanations

    various contexts

    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
    ﺒ
    0.45
    の変化
    0.44
    ieť
    0.44
    Tooth
    0.43
     guerra
    0.43
    ן
    0.42
    ଝ
    0.42
    ИН
    0.42
     যুদ্ধের
    0.41
    rač
    0.41
    POSITIVE LOGITS
     Side
    0.48
     Length
    0.46
     Circum
    0.45
     Folder
    0.44
     Tenure
    0.44
    ügel
    0.44
     CAA
    0.43
     SDK
    0.42
     område
    0.42
     Latter
    0.41
    Activations Density 0.003%

    No Known Activations