© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42876
    Prev
    Next
    INDEX
    Explanations

    words tend to follow other 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
    敬
    0.46
    mfenced
    0.45
    比較
    0.43
     కలిగి
    0.43
    Ử
    0.43
    ử
    0.42
    保持
    0.42
    偵
    0.41
    在使用
    0.41
    任務
    0.40
    POSITIVE LOGITS
     trwa
    0.53
    دی
    0.52
     macchina
    0.49
     Beni
    0.49
     aparel
    0.48
     impulsar
    0.48
     impres
    0.48
     pesce
    0.48
     reuni
    0.47
     odit
    0.46
    Activations Density 0.003%

    No Known Activations