© 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. 182676
    Prev
    Next
    INDEX
    Explanations

    foreign language or word usage

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

    data storage and retrieval

    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
     \
    0.46
    ker
    0.46
    keras
    0.46
    nias
    0.45
    spring
    0.44
    kaar
    0.44
    legas
    0.44
    ners
    0.43
    cha
    0.43
    ceral
    0.43
    POSITIVE LOGITS
     lateribus
    0.54
    手の
    0.53
     edizione
    0.52
     ܥ
    0.51
     appliquer
    0.51
    
    0.50
     édition
    0.50
    lcii
    0.50
    ສ
    0.50
     ඉක්
    0.49
    Activations Density 0.000%

    No Known Activations