© 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. 182141
    Prev
    Next
    INDEX
    Explanations

    predictive technology and winners

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

    no less

    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
    Έ
    0.50
    آ
    0.50
    ಒ
    0.48
    δη
    0.48
    珅
    0.47
    нной
    0.46
     Eğer
    0.46
     Jeżeli
    0.46
    کل
    0.46
     він
    0.45
    POSITIVE LOGITS
     carc
    0.47
     المعاد
    0.47
    egn
    0.46
     personally
    0.45
    onden
    0.45
     remuneration
    0.43
    PWD
    0.43
    cede
    0.42
    efic
    0.42
    掠
    0.42
    Activations Density 0.000%

    No Known Activations