© 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. 13767
    Prev
    Next
    INDEX
    Explanations

    descriptive adjective noun pairs

    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
    ླ
    1.57
     unmittelbar
    1.54
    いただける
    1.52
    ttä
    1.51
    नातील
    1.51
    rzez
    1.50
    letak
    1.48
    otherapeutic
    1.45
    umpulan
    1.44
    ņem
    1.44
    POSITIVE LOGITS
    ↵
    1.84
     Quite
    1.63
     Sadly
    1.41
    <end_of_image>
    1.41
     That
    1.37
     Caps
    1.34
     Today
    1.32
     Also
    1.31
     Then
    1.30
     пар
    1.29
    Activations Density 0.058%

    No Known Activations