© 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. 28833
    Prev
    Next
    INDEX
    Explanations

    email notifications

    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
     marvellous
    0.44
    ቲክ
    0.43
    ➰
    0.43
    镟
    0.43
    撳
    0.43
     तिलावत
    0.42
     যাইতেছে
    0.41
    🉑
    0.41
    
    0.41
     tunnelling
    0.41
    POSITIVE LOGITS
    cos
    0.44
     bi
    0.38
     +
    0.37
     ras
    0.37
     -
    0.37
    ::
    0.36
    Red
    0.36
    0.36
    Â
    0.36
     Wat
    0.36
    Activations Density 0.000%

    No Known Activations