© 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. 75313
    Prev
    Next
    INDEX
    Explanations

    special care, lifestyle, events

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

    legal contracts and summarization

    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
    䡉
    0.46
    Compounds
    0.44
     فهم
    0.43
     আলো
    0.42
     ihn
    0.42
    न्थ
    0.42
     Compounds
    0.41
     кандида
    0.41
    نيف
    0.41
    nCurr
    0.41
    POSITIVE LOGITS
    ey
    0.48
     परिस्थित
    0.47
    pro
    0.46
    ill
    0.46
     gota
    0.45
    1
    0.44
     முழுவதும்
    0.43
     croche
    0.43
    uet
    0.43
    agis
    0.43
    Activations Density 0.001%

    No Known Activations