© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6116
    Prev
    Next
    INDEX
    Explanations

    Armenian and international words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     monolayer
    0.49
     analytic
    0.46
     anarchist
    0.46
     olhar
    0.45
     microorgan
    0.45
    শিয়া
    0.44
    𒌍
    0.44
     anggaran
    0.44
     synthesizer
    0.43
     anatomic
    0.43
    POSITIVE LOGITS
    В
    0.44
     ||
    0.40
     Otter
    0.39
     //
    0.38
     While
    0.37
    tir
    0.36
    !
    0.36
    owie
    0.35
     Tolkien
    0.35
     Stal
    0.35
    Activations Density 0.001%

    No Known Activations