© 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-65K
    7. 6991
    Prev
    Next
    INDEX
    Explanations

    mathematical even/odd statements

    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_65k_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
    𝐬
    0.48
    ärke
    0.48
    <unused2026>
    0.48
     energii
    0.46
    lcii
    0.46
    waitForIdleSync
    0.46
    <unused0>
    0.45
     القيم
    0.44
     obras
    0.44
    を設定
    0.44
    POSITIVE LOGITS
        
    0.48
            
    0.47
     в
    0.45
    在
    0.45
     equine
    0.43
    ใน
    0.43
     in
    0.42
    좁
    0.42
     всему
    0.41
     motorists
    0.41
    Activations Density 0.004%

    No Known Activations