© 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. 97446
    Prev
    Next
    INDEX
    Explanations

    completing words

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

    dissecting laws, understanding, greetings

    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
     कामया
    0.51
    聁
    0.51
     चार्ल्स
    0.50
    vā
    0.50
     포함
    0.49
     બીજા
    0.49
     محر
    0.48
     குதிக
    0.47
    цией
    0.47
     स्त
    0.47
    POSITIVE LOGITS
    0.55
     g
    0.50
     ch
    0.45
    )
    0.45
     prim
    0.43
     gost
    0.43
     correo
    0.43
     grove
    0.42
     f
    0.42
     DMC
    0.41
    Activations Density 0.000%

    No Known Activations