© 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. 138814
    Prev
    Next
    INDEX
    Explanations

    `details` `answer` `recall` `single`

    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
     v
    0.50
     al
    0.50
     persistently
    0.49
     forest
    0.47
     den
    0.47
     till
    0.46
     voit
    0.46
     ra
    0.45
     woman
    0.45
     sweet
    0.43
    POSITIVE LOGITS
    ໄປ
    0.55
     સંખ્યા
    0.52
    loj
    0.52
    艰难
    0.50
    绘制
    0.49
    哆
    0.49
    凯
    0.49
    锋
    0.48
    法规
    0.47
     కీలక
    0.46
    Activations Density 0.005%

    No Known Activations