© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10015
    Prev
    Next
    INDEX
    Explanations

    with disabilities

    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
    .​
    1.19
    chi
    1.09
    .​​
    1.08
     irrespective
    1.04
     못한
    1.01
     spelt
    1.00
    Orm
    0.98
    coloured
    0.98
     पार्वती
    0.98
    .
    0.97
    POSITIVE LOGITS
     Organized
    1.28
    常规
    1.28
     Utilis
    1.27
     Structured
    1.25
     Selective
    1.23
    ビック
    1.22
     Supervisory
    1.20
     Ef
    1.19
     prototypical
    1.19
     Einf
    1.18
    Activations Density 0.000%

    No Known Activations