© 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. 15964
    Prev
    Next
    INDEX
    Explanations

    even still

    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
     although
    0.61
    雖
    0.58
    虽然
    0.57
     zwar
    0.55
    虽
    0.55
     хотя
    0.54
    雖然
    0.53
     nejen
    0.53
     embora
    0.52
    不仅
    0.52
    POSITIVE LOGITS
     vẫn
    0.68
     tetap
    0.66
    仍
    0.63
     fortfarande
    0.62
    still
    0.57
     still
    0.56
    仍然
    0.56
     masih
    0.55
     stále
    0.55
    Still
    0.54
    Activations Density 0.104%

    No Known Activations