© 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. 2716
    Prev
    Next
    INDEX
    Explanations

    brand names and product prefixes

    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
    0.67
     the
    0.67
     great
    0.65
    ly
    0.65
    ↵↵
    0.64
      
    0.63
    ,
    0.63
     stands
    0.63
    ...
    0.62
     value
    0.61
    POSITIVE LOGITS
     brems
    0.94
     Rennen
    0.86
    ༤
    0.85
     PlayerSelector
    0.85
     Oldborough
    0.85
     Fmat
    0.84
    LOTRE
    0.83
     Drog
    0.83
    ંટણી
    0.82
     راجس
    0.82
    Activations Density 0.148%

    No Known Activations