© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8902
    Prev
    Next
    INDEX
    Explanations

    cor, corruption, corrosion, correlation, coronal, coriander, coroutines

    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_16k_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
     sued
    0.41
     questioned
    0.39
     juggling
    0.38
    缬
    0.37
    ამო
    0.37
    ᡤ
    0.37
     목
    0.37
    kusen
    0.37
     analys
    0.36
    婜
    0.36
    POSITIVE LOGITS
    Cor
    1.80
     Cor
    1.69
     cor
    1.59
    cor
    1.59
     kor
    1.56
     COR
    1.50
     кор
    1.47
    腐
    1.47
     Kor
    1.45
    COR
    1.38
    Activations Density 0.107%

    No Known Activations