© 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. 31-GEMMASCOPE-2-RES-262K
    7. 43264
    Prev
    Next
    INDEX
    Explanations

    encoding and decoding

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

    base64 encoding and decoding

    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
    фта
    0.51
    Rivers
    0.43
    ︠
    0.41
    Nicolas
    0.40
    Laurie
    0.40
    郦
    0.40
    ENEMY
    0.40
    绯
    0.40
    це
    0.40
    个性
    0.39
    POSITIVE LOGITS
     encoded
    0.56
    decode
    0.53
     Decoding
    0.51
    encoded
    0.49
     decoded
    0.48
     Encode
    0.47
     decode
    0.47
    encode
    0.46
     decoding
    0.46
     Converting
    0.46
    Activations Density 0.005%

    No Known Activations