© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 837
    Prev
    Next
    INDEX
    Explanations

    conditional clauses and consequences

    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_65k_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
    ات
    1.18
    s
    1.05
    ి
    1.04
    ‌ی
    0.99
    قتها
    0.99
    restassured
    0.98
    dür
    0.95
    ക്ക്‌
    0.95
    اتها
    0.95
    grav
    0.89
    POSITIVE LOGITS
    ary
    1.26
    ever
    1.22
    eci
    1.10
    ek
    1.09
    ec
    1.07
    머니
    1.05
    ポーツ
    1.05
     ສ
    1.04
    𝙝
    1.01
    𝐡
    1.01
    Activations Density 0.691%

    No Known Activations