© 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. 100179
    Prev
    Next
    INDEX
    Explanations

    lists and examples

    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
    он
    0.45
    Ngày
    0.44
    첨
    0.44
    ѣ
    0.43
     dalších
    0.43
     febrero
    0.43
    ujesz
    0.41
    발
    0.41
    ख़
    0.41
    ujących
    0.41
    POSITIVE LOGITS
    ینا
    0.49
     COT
    0.49
     دوست
    0.48
     منظ
    0.46
    <unused216>
    0.46
     برم
    0.44
     دانشگاه
    0.43
     adhipp
    0.43
     بلد
    0.43
    ukk
    0.42
    Activations Density 0.001%

    No Known Activations