© 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. 222624
    Prev
    Next
    INDEX
    Explanations

    upper triangular matrix

    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
    हरादून
    0.40
     olho
    0.40
     आंख
    0.40
    𝘈
    0.39
    Mango
    0.38
     глаза
    0.38
    платно
    0.37
     longe
    0.37
    
    0.37
    Getting
    0.36
    POSITIVE LOGITS
     inciting
    0.38
     Miyazaki
    0.38
     conmigo
    0.37
     modeli
    0.37
     Hogan
    0.36
     অগ্রসর
    0.36
     propagand
    0.36
     dard
    0.36
     subsec
    0.35
     여기가
    0.35
    Activations Density 0.000%

    No Known Activations