© 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. 212689
    Prev
    Next
    INDEX
    Explanations

    alternatives or questions

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

    the end of sentences and phrases

    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
     Mailing
    0.51
     গেছে
    0.49
     Scheduling
    0.48
    琪
    0.47
     specialization
    0.47
     করলেও
    0.46
     সভা
    0.45
     Societe
    0.44
     कन्या
    0.44
     Mädchen
    0.44
    POSITIVE LOGITS
    ing
    0.52
    ة
    0.49
    qu
    0.49
     ກຳ
    0.48
     slabs
    0.46
    io
    0.46
     parallèles
    0.45
    uant
    0.45
    ia
    0.44
     antiqu
    0.44
    Activations Density 0.002%

    No Known Activations