© 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. 89821
    Prev
    Next
    INDEX
    Explanations

    credit card number

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

    modern clinical or scientific terms

    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
     envis
    0.47
    ガン
    0.46
     envisage
    0.46
     revenues
    0.44
     reckons
    0.44
     dupatta
    0.43
     forecasts
    0.42
    洟
    0.42
     بلغ
    0.41
     envisaged
    0.41
    POSITIVE LOGITS
    还是
    0.63
     moderne
    0.57
    神经
    0.53
    现代
    0.52
    Modern
    0.51
    临床
    0.51
     neurologic
    0.49
    洍
    0.48
    迨
    0.47
    Neu
    0.46
    Activations Density 0.001%

    No Known Activations