© 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. 123753
    Prev
    Next
    INDEX
    Explanations

    password

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

    password input and assignment

    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
    Negative Logits
    .
    0.62
     पासवर्ड
    0.57
    密钥
    0.53
     Keychain
    0.51
     passcode
    0.50
    통
    0.50
     Venom
    0.49
     encrypt
    0.49
     password
    0.48
     सपना
    0.48
    POSITIVE LOGITS
    E
    0.60
    X
    0.58
    O
    0.57
    ޝ
    0.57
    F
    0.57
    an
    0.55
    for
    0.55
    V
    0.54
    ov
    0.54
    াতের
    0.53
    Activations Density 0.003%

    No Known Activations