© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15594
    Prev
    Next
    INDEX
    Explanations

    impressed with

    np_acts-logits-general · gemini-2.5-flash-lite

    impressed by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     मुसीबत
    0.58
     आपल्याला
    0.57
     discomfort
    0.55
     frustrating
    0.53
     irritating
    0.51
     कष्ट
    0.51
    俚
    0.50
    )
    0.49
     sufrimiento
    0.49
    疑
    0.49
    POSITIVE LOGITS
    impress
    0.61
     impressively
    0.60
     impressive
    0.60
     beeindruck
    0.59
     zuerst
    0.59
     впечат
    0.57
    Impress
    0.57
     odmah
    0.57
     vollständ
    0.56
     impres
    0.54
    Activations Density 0.021%

    No Known Activations