Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8451
    Prev
    Next
    INDEX
    Explanations

    invisible or stealth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    мых
    -0.96
    mbal
    -0.84
     знаний
    -0.81
    Vien
    -0.81
    estrogen
    -0.81
    Interactive
    -0.81
    磊
    -0.77
     کند
    -0.74
    umburg
    -0.72
    윈
    -0.71
    POSITIVE LOGITS
     invisible
    3.75
     Invisible
    3.17
    invisible
    3.17
    Invisible
    2.84
     invis
    2.59
    visibility
    2.52
    INVISIBLE
    2.22
     visibility
    2.11
     Invis
    2.03
     cloak
    1.91
    Activations Density 0.026%

    No Known Activations