© 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. 11531
    Prev
    Next
    INDEX
    Explanations

    document dates

    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
     LF
    1.19
     குறைவாக
    1.15
     섹
    1.15
    なかった
    1.14
    だった
    1.14
    LF
    1.12
    minimal
    1.12
     দিয়েছিল
    1.12
     最
    1.11
     iTunes
    1.09
    POSITIVE LOGITS
     hereby
    1.44
     hereof
    1.31
     позна
    1.10
     undersigned
    1.08
     цей
    1.08
     herewith
    1.07
     detta
    1.03
     дан
    1.00
     hereto
    0.96
     данный
    0.96
    Activations Density 0.096%

    No Known Activations