© 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. 29165
    Prev
    Next
    INDEX
    Explanations

    not yet, authors than, May the

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

    named entity recognition

    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
    о
    0.57
    є
    0.55
     আশ্চর্যজনক
    0.49
     ljudi
    0.48
     جانتے
    0.48
    ма
    0.47
    і
    0.46
    а
    0.46
     doesn
    0.45
    ốt
    0.45
    POSITIVE LOGITS
    ＂
    0.54
     (<
    0.52
    出一
    0.52
    淞
    0.48
     “(
    0.46
    或
    0.46
    出了
    0.46
    らった
    0.45
     Atti
    0.45
     EF
    0.44
    Activations Density 0.000%

    No Known Activations