© 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. 11103
    Prev
    Next
    INDEX
    Explanations

    listing directories

    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
     standard
    1.28
    ំពោះ
    1.28
     aude
    1.28
    ized
    1.25
    uc
    1.25
    cid
    1.25
    standard
    1.22
    Ь
    1.21
     substantive
    1.21
    म्ब
    1.16
    POSITIVE LOGITS
    Unlike
    1.97
    Although
    1.85
    Vu
    1.73
    Close
    1.73
    While
    1.66
     Unlike
    1.64
    Además
    1.63
    Anche
    1.62
    Generally
    1.61
    Não
    1.60
    Activations Density 0.021%

    No Known Activations