© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14784
    Prev
    Next
    INDEX
    Explanations

    vulnerability of people or systems

    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_13_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
    муля
    1.88
     $)$.
    1.83
    hes
    1.80
    klass
    1.76
    rans
    1.72
     megt
    1.72
    ause
    1.72
    মির
    1.70
    мулятор
    1.68
    esu
    1.67
    POSITIVE LOGITS
     exposed
    2.18
    暴露
    2.05
    きゃ
    2.02
     каттоо
    1.93
    露
    1.92
    astly
    1.91
    ѕ
    1.91
     exposing
    1.87
    露出
    1.86
    exposed
    1.82
    Activations Density 0.197%

    No Known Activations