© 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. 77035
    Prev
    Next
    INDEX
    Explanations

    breakdown of differences

    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
    nya
    0.55
    angnya
    0.49
     করিয়াছিল
    0.46
     supera
    0.46
     mycel
    0.46
    ceased
    0.45
    γα
    0.44
    _{-}\
    0.44
     ہوا۔
    0.43
     catalyzes
    0.43
    POSITIVE LOGITS
    чик
    0.48
     Melanie
    0.47
    我们
    0.46
    ➸
    0.45
    Objective
    0.44
     Stephanie
    0.44
    ྥ
    0.44
     Caroline
    0.44
     जोखिम
    0.44
     we
    0.43
    Activations Density 0.001%

    No Known Activations