© 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. 4507
    Prev
    Next
    INDEX
    Explanations

    Filipino prefixes and word fragments

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

    Korean and Southeast Asian syllables

    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
     meines
    0.26
     Kapitel
    0.24
     którego
    0.24
    ３
    0.24
     waarvan
    0.23
    FOUR
    0.23
    ４
    0.23
    ください
    0.23
     तुम्ही
    0.22
     которого
    0.22
    POSITIVE LOGITS
     sustain
    0.21
     lucrative
    0.20
     নৈতিক
    0.19
    u
    0.19
     economic
    0.19
     consistent
    0.19
     compelling
    0.19
     trade
    0.19
     geopolitical
    0.19
    o
    0.19
    Activations Density 0.011%

    No Known Activations