© 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. 14257
    Prev
    Next
    INDEX
    Explanations

    adult content or jokes

    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
    哨
    1.27
     Tài
    1.25
     ثلاث
    1.23
    撂
    1.22
    Days
    1.22
    ㎞
    1.21
     quãng
    1.18
    的天
    1.17
    靂
    1.17
     ăn
    1.17
    POSITIVE LOGITS
     generalizations
    1.59
     necessarily
    1.54
     generalizing
    1.53
     ubiquitous
    1.50
     beginner
    1.47
     generalization
    1.44
     generalize
    1.43
     universal
    1.43
     unpleasant
    1.43
     often
    1.43
    Activations Density 0.001%

    No Known Activations