© 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. 257028
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     καλ
    0.47
    一线
    0.47
    icions
    0.46
    arial
    0.46
     помогают
    0.45
    寿
    0.44
    িল্প
    0.44
     უკ
    0.43
     لوبې
    0.42
    wunsch
    0.42
    POSITIVE LOGITS
    ERK
    0.51
    다른
    0.49
    ্যান্ড
    0.47
    کہ
    0.46
     comentarios
    0.45
    KUR
    0.45
    </h6>
    0.45
    tens
    0.44
    ओके
    0.44
    DEFGHI
    0.43
    Activations Density 0.002%

    No Known Activations