© 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. 77058
    Prev
    Next
    INDEX
    Explanations

    remember instructions forgotten

    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
     مكان
    0.54
    迸
    0.54
     अधिनियम
    0.52
     място
    0.49
     ಹ
    0.48
     ನೀಡ
    0.48
     നിയമ
    0.47
     المكان
    0.47
     ಗುರು
    0.47
    വ്വ
    0.46
    POSITIVE LOGITS
     isn
    0.42
     chunky
    0.41
     mold
    0.40
    ющихся
    0.39
     ++
    0.39
     leaky
    0.39
    тся
    0.38
    아요
    0.38
     thumbs
    0.38
     watered
    0.37
    Activations Density 0.012%

    No Known Activations