© 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. 1367
    Prev
    Next
    INDEX
    Explanations

    structured information

    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
    Puede
    0.48
    นำ
    0.47
    용
    0.46
    ุ
    0.46
    ร
    0.45
    กลับ
    0.44
    은
    0.44
    ן
    0.44
    nc
    0.44
    י
    0.44
    POSITIVE LOGITS
     iteratively
    0.61
     scripted
    0.51
     iterated
    0.50
     describe
    0.48
     describes
    0.46
     ℝ
    0.46
     bureaucrats
    0.45
     organized
    0.45
     explored
    0.45
     dozens
    0.45
    Activations Density 0.001%

    No Known Activations