© 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. 40-GEMMASCOPE-2-RES-262K
    7. 16346
    Prev
    Next
    INDEX
    Explanations

    togetherness

    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_40_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
     якая
    0.45
     друг
    0.42
    ্টি
    0.39
     elkaar
    0.39
    ربية
    0.39
     אשר
    0.38
     birbir
    0.38
    );
    0.38
     و
    0.38
     বহ
    0.38
    POSITIVE LOGITS
    la
    0.50
    라
    0.49
    라는
    0.46
    óm
    0.45
    라면
    0.45
    는
    0.44
    라서
    0.43
    Escol
    0.42
    ಯೇ
    0.41
    ა
    0.41
    Activations Density 0.011%

    No Known Activations