© 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. 16778
    Prev
    Next
    INDEX
    Explanations

    English phrases near foreign words

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

    proof of reserves

    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
     This
    0.58
     Disclosure
    0.49
     Moreover
    0.45
     It
    0.44
     Scheme
    0.44
     و
    0.44
     Language
    0.44
     Date
    0.43
     Lay
    0.43
     Adding
    0.43
    POSITIVE LOGITS
     campuran
    0.52
     spok
    0.49
    protos
    0.48
     karoti
    0.46
     પ્રો
    0.46
     murió
    0.46
     vattum
    0.46
    ینڈ
    0.44
    ্টর
    0.44
    Ṕ
    0.44
    Activations Density 0.000%

    No Known Activations