© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8384
    Prev
    Next
    INDEX
    Explanations

    introducing examples or instances

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

    introducing assumptions

    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_40_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
    在这里
    0.49
     여기서
    0.47
    今回は
    0.44
     यावेळी
    0.43
    在本
    0.43
    PointSize
    0.41
    KeyListener
    0.41
    ⅜
    0.40
     그대로
    0.40
    ोजना
    0.38
    POSITIVE LOGITS
    every
    0.42
    導致
    0.42
    导致
    0.41
    SimpleDateFormat
    0.41
    simpl
    0.40
    ahm
    0.40
     anniversaire
    0.39
    periode
    0.39
    imagine
    0.39
    say
    0.39
    Activations Density 0.001%

    No Known Activations