© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7406
    Prev
    Next
    INDEX
    Explanations

    PHP code constructs

    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_22_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
     php
    1.44
     PHP
    1.34
    php
    1.31
    PHP
    1.21
    邝
    1.07
     Filipino
    1.03
     Philippine
    1.00
     Ennis
    0.99
    Laravel
    0.98
     Laravel
    0.94
    POSITIVE LOGITS
    $
    1.09
     $
    1.01
     Judaism
    0.90
     Confederacy
    0.90
     Macc
    0.90
     ${{
    0.90
    kish
    0.89
     Ecosystem
    0.89
     Reconciliation
    0.89
     $\
    0.88
    Activations Density 0.005%

    No Known Activations