© 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. 41546
    Prev
    Next
    INDEX
    Explanations

    code and explanations

    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
    缟
    0.42
    吃了
    0.39
    RENCE
    0.39
     trúc
    0.38
    generally
    0.38
     rerum
    0.38
     بسم
    0.38
    这是一个
    0.38
     Министерство
    0.37
    ována
    0.37
    POSITIVE LOGITS
     مذکور
    0.50
    4
    0.41
    ]
    0.41
    3
    0.38
    ]<<"
    0.38
    ivet
    0.36
    ]];
    0.36
    win
    0.36
     감
    0.36
     aforementioned
    0.36
    Activations Density 0.002%

    No Known Activations