© 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. 11271
    Prev
    Next
    INDEX
    Explanations

    describes following tokens

    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
    .}(
    1.43
    multline
    1.42
     листь
    1.42
     לכ
    1.42
     yanlı
    1.40
    쾺
    1.39
     finalement
    1.38
     yeniden
    1.37
    agregar
    1.34
     উদ্ভি
    1.34
    POSITIVE LOGITS
     member
    0.99
     auditing
    0.99
     Organisation
    0.99
    구요
    0.97
     Specified
    0.95
     registered
    0.92
     accredited
    0.92
     �
    0.90
     therefore
    0.89
     yes
    0.87
    Activations Density 0.000%

    No Known Activations