© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3334
    Prev
    Next
    INDEX
    Explanations

    models, demos, offsetting

    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_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
    सभी
    0.54
    இந்த
    0.53
    Cela
    0.53
    effectuer
    0.53
    ır
    0.52
    ס
    0.52
    अमेरिकी
    0.51
    ת
    0.50
    ור
    0.49
    crast
    0.49
    POSITIVE LOGITS
     S
    0.48
     non
    0.48
     B
    0.48
     M
    0.47
     Ch
    0.47
     P
    0.46
     High
    0.46
     Echin
    0.45
     One
    0.45
     A
    0.44
    Activations Density 0.292%

    No Known Activations