© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1653
    Prev
    Next
    INDEX
    Explanations

    how things work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    则
    0.83
     when
    0.82
    則是
    0.80
     during
    0.78
    ?
    0.78
     이때
    0.75
    when
    0.75
     podczas
    0.75
    則
    0.74
     এসময়
    0.74
    POSITIVE LOGITS
     exists
    1.35
     existed
    1.20
     fonctionne
    1.19
     operates
    1.17
     mattered
    1.16
     funktioniert
    1.15
     functioned
    1.10
     funciona
    1.08
     funzion
    1.08
     might
    1.07
    Activations Density 0.550%

    No Known Activations