© 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. 16-GEMMASCOPE-2-RES-262K
    7. 875
    Prev
    Next
    INDEX
    Explanations

    direct address to you

    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_16_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
    ス
    0.46
    வட
    0.41
     école
    0.40
     усіх
    0.40
    يارات
    0.39
    스는
    0.38
    ليم
    0.38
     regiões
    0.38
    N
    0.38
    色が
    0.38
    POSITIVE LOGITS
    на
    0.55
    ;
    0.54
    x
    0.45
    ın
    0.45
    ع
    0.45
     (
    0.44
     i
    0.43
    ,
    0.42
    ↵
    0.42
     सुमारे
    0.42
    Activations Density 0.089%

    No Known Activations