© 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. 116370
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    warnings and important notes

    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
    вов
    0.48
    簋
    0.47
     населення
    0.46
    −</
    0.45
     ਰਾ
    0.45
    ሠራ
    0.44
    Legend
    0.44
     ಪೂರ್ವ
    0.43
    &(
    0.43
     Леон
    0.43
    POSITIVE LOGITS
     doorstep
    0.50
     vostre
    0.49
     książ
    0.49
    他说
    0.47
     değerli
    0.46
     abordar
    0.46
     bestow
    0.46
     আপনার
    0.46
     jego
    0.46
     ustedes
    0.45
    Activations Density 0.001%

    No Known Activations