© 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. 15676
    Prev
    Next
    INDEX
    Explanations

    after, then, thereafter

    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
     dampers
    0.49
     entirety
    0.45
     clipped
    0.44
     cheats
    0.43
     easements
    0.42
    ····
    0.41
     thirty
    0.41
    3
    0.40
     exported
    0.39
     rubs
    0.39
    POSITIVE LOGITS
     समस्या
    0.46
    स्तर
    0.45
     setelah
    0.44
     विचार
    0.43
    徎
    0.43
     بعد
    0.42
    淑
    0.42
     बदलाव
    0.42
     após
    0.42
     लक्षण
    0.41
    Activations Density 0.001%

    No Known Activations