© 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. 96602
    Prev
    Next
    INDEX
    Explanations

    nearest airport is

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

    words replaced or changed

    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
    xl
    0.47
    Jet
    0.46
    lat
    0.42
     ulc
    0.42
    Species
    0.40
    recall
    0.39
    Snackbar
    0.39
    >(</
    0.39
    Swap
    0.39
    hala
    0.39
    POSITIVE LOGITS
    बई
    0.54
    柰
    0.54
     navn
    0.52
     patriots
    0.52
    警方
    0.51
     saucepan
    0.51
    ماية
    0.49
    ون
    0.48
     Protección
    0.48
    ्ञ
    0.48
    Activations Density 0.000%

    No Known Activations