© 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. 190919
    Prev
    Next
    INDEX
    Explanations

    stretch out

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

    business terms and concepts

    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
     করায়
    0.51
    远
    0.48
    राधना
    0.45
     elő
    0.45
    Paragraph
    0.45
    篪
    0.45
     endroits
    0.43
    转向
    0.43
    处
    0.43
     nyug
    0.42
    POSITIVE LOGITS
    azada
    0.54
    ari
    0.53
    ugh
    0.52
     इस्ला
    0.49
     एक्सेल
    0.49
    uploader
    0.48
    ono
    0.47
    novation
    0.47
    uy
    0.46
     ઉપ
    0.46
    Activations Density 0.001%

    No Known Activations