© 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. 53152
    Prev
    Next
    INDEX
    Explanations

    newness and recency

    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
    时
    0.42
     stepwise
    0.39
     earlier
    0.38
    時
    0.38
     مرة
    0.37
    വന
    0.37
     increments
    0.36
    ign
    0.36
    無視
    0.36
    ustible
    0.36
    POSITIVE LOGITS
    短短
    0.66
     짧
    0.64
    짧
    0.59
     henüz
    0.56
     এরই
    0.55
     yet
    0.54
    短い
    0.53
     अपेक्षाकृत
    0.52
     ännu
    0.52
     Yet
    0.51
    Activations Density 0.045%

    No Known Activations