© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178258
    Prev
    Next
    INDEX
    Explanations

    trail running, contract, opportunity in, Proximal Development

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

    different languages or numerical concepts

    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
    Negative Logits
     příjem
    0.49
     làm
    0.45
    apple
    0.43
     күз
    0.43
     farm
    0.43
     প্রশাসনের
    0.42
    "/><
    0.41
    採
    0.41
     wellbeing
    0.41
     báo
    0.41
    POSITIVE LOGITS
    獨立
    0.47
     Designated
    0.46
    該
    0.46
     phases
    0.45
     cuadrada
    0.45
    Phase
    0.45
    ஸ்தான
    0.45
    Elementos
    0.44
    designated
    0.44
     Punkte
    0.43
    Activations Density 0.001%

    No Known Activations