Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 50798
    Prev
    Next
    INDEX
    Explanations

    "company" and "time" words

    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
    ⇜
    0.46
    Come
    0.46
    .«
    0.45
     Cleanup
    0.44
    hare
    0.44
    Colors
    0.44
    ."[
    0.44
    酺
    0.44
     পার্
    0.43
    puff
    0.43
    POSITIVE LOGITS
     aika
    0.48
     علی
    0.47
     સમયે
    0.45
     especializada
    0.45
     especializado
    0.44
     zaman
    0.43
    ла
    0.43
     luj
    0.42
     civilization
    0.41
    รม
    0.41
    Activations Density 0.001%

    No Known Activations