© 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. 40-GEMMASCOPE-2-RES-262K
    7. 33692
    Prev
    Next
    INDEX
    Explanations

    recognize country, relations

    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_40_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
    tfidf
    0.47
    
    0.46
    ទ្
    0.42
    彪
    0.39
     bhavati
    0.39
    lidir
    0.38
    ッドレス
    0.38
     sonucu
    0.38
    Результа
    0.37
    formula
    0.37
    POSITIVE LOGITS
     impeding
    0.40
     depress
    0.39
    दरी
    0.38
    択
    0.38
     wrongful
    0.37
     Ry
    0.37
     जुल
    0.37
     barring
    0.37
     Weigh
    0.37
     weighing
    0.36
    Activations Density 0.000%

    No Known Activations