© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3666
    Prev
    Next
    INDEX
    Explanations

    individuals and families

    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
    ونَ
    2.43
    áját
    2.28
    ень
    2.21
    繇
    2.20
    ças
    2.16
    ซ์
    2.15
    入荷
    2.14
    勰
    2.14
    BigAutoField
    2.13
    ब्ल्यू
    2.13
    POSITIVE LOGITS
     classify
    3.17
     identify
    3.00
     assert
    2.98
     promote
    2.95
     destroy
    2.94
     reinforce
    2.92
     encourage
    2.88
     admit
    2.88
     purify
    2.87
     adhere
    2.86
    Activations Density 0.898%

    No Known Activations