© 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. 37210
    Prev
    Next
    INDEX
    Explanations

    are not or have not

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

    deleting items, predicting

    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
    E
    0.52
    EC
    0.50
    Е
    0.48
    専用
    0.47
    э
    0.47
    ク
    0.47
    ES
    0.46
    座
    0.46
    ετε
    0.46
    Э
    0.46
    POSITIVE LOGITS
     nejsou
    0.62
     geprüft
    0.54
     olmadığı
    0.54
     ബ്രി
    0.51
     není
    0.49
     behandelt
    0.48
     നിരവധി
    0.48
     gesam
    0.47
     gegründet
    0.47
     করায়
    0.47
    Activations Density 0.000%

    No Known Activations