© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9632
    Prev
    Next
    INDEX
    Explanations

    inline with

    np_acts-logits-general · gemini-2.5-flash-lite

    emotions, knowledge, airport, intention, processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     have
    0.58
      
    0.48
     aid
    0.47
     llave
    0.46
    빛
    0.46
     was
    0.45
    고
    0.45
     chari
    0.44
     Key
    0.43
     adev
    0.43
    POSITIVE LOGITS
     США
    0.55
    比賽
    0.51
     захворю
    0.49
    ες
    0.48
     України
    0.48
     पाकिस्तान
    0.48
    觀眾
    0.47
    orsement
    0.47
    駙
    0.47
     ಪ್ರಕರಣ
    0.47
    Activations Density 0.000%

    No Known Activations