© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3844
    Prev
    Next
    INDEX
    Explanations

    security risks and breaches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    फारिश
    2.93
    ി
    2.76
    ه
    2.60
    jetbrains
    2.55
    prä
    2.50
    ognito
    2.50
    epar
    2.49
    া
    2.46
    eof
    2.45
    gener
    2.40
    POSITIVE LOGITS
    ishly
    3.01
    otions
    2.83
    焼き
    2.78
    ಗ
    2.77
    SOCKET
    2.76
    pción
    2.73
     rospy
    2.73
    स्वी
    2.72
    وید
    2.72
     targ
    2.72
    Activations Density 0.048%

    No Known Activations