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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 9413
    Prev
    Next
    INDEX
    Explanations

    unauthorized disclosure

    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
     concurrent
    0.86
    idega
    0.80
    สุดท้าย
    0.80
    teki
    0.78
    最高的
    0.78
     Initially
    0.77
     Depending
    0.77
     }}-
    0.77
     IHC
    0.76
    }}/
    0.76
    POSITIVE LOGITS
     julio
    1.24
     kinderen
    1.21
    怀孕
    1.20
     tomatoes
    1.18
     criaturas
    1.18
     aventuras
    1.17
     revolutionized
    1.17
     springtime
    1.14
     veggies
    1.14
     सेलिब्र
    1.14
    Activations Density 0.000%

    No Known Activations