© 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-262K
    7. 123975
    Prev
    Next
    INDEX
    Explanations

    sharing pre-trained models

    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_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
     तीर्थ
    0.46
     wisata
    0.46
    ദ്ധ
    0.44
    વ
    0.44
    सु
    0.43
    ش
    0.42
     Sự
    0.41
    ൊന്ന
    0.41
    ש
    0.41
    سٹر
    0.41
    POSITIVE LOGITS
     extruded
    0.47
     marbled
    0.46
     browned
    0.46
    ILI
    0.44
     смотре
    0.41
     сом
    0.40
     sombrero
    0.40
    ។
    0.39
    噔
    0.39
    ONES
    0.39
    Activations Density 0.004%

    No Known Activations