© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3071
    Prev
    Next
    INDEX
    Explanations

    code definitions or structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    .(*
    1.80
    。
    1.66
    。『
    1.63
    。「
    1.61
    。...
    1.60
     whom
    1.56
    .。
    1.54
    .";
    1.53
    .[
    1.52
    .
    1.50
    POSITIVE LOGITS
     vẫn
    1.68
     blijft
    1.66
     pode
    1.49
     blir
    1.45
    기는
    1.37
     kommer
    1.37
     נמצא
    1.36
     bleibt
    1.36
    ก็
    1.35
     può
    1.35
    Activations Density 0.001%

    No Known Activations