© 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. 195046
    Prev
    Next
    INDEX
    Explanations

    multilingual words and phrases

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

    strategy and outcomes

    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
    는
    0.56
     authentic
    0.50
     orthodox
    0.47
     ortodox
    0.45
    osing
    0.44
    Air
    0.44
    Ireland
    0.44
     ung
    0.44
    Audio
    0.43
    &
    0.43
    POSITIVE LOGITS
     দৌ
    0.50
    捃
    0.50
     गुंत
    0.49
    dimensioni
    0.49
     Complaint
    0.47
     तक्र
    0.47
     труда
    0.47
    μάτων
    0.46
     базу
    0.46
     використа
    0.46
    Activations Density 0.000%

    No Known Activations